© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 18-TRANSCODER-HP
    7. 89229
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĹ¶ä»£
    -0.26
     Boyd
    -0.26
     Crash
    -0.25
    ropa
    -0.25
    è¸Ĭè·ĥ
    -0.25
    toa
    -0.25
     -------------------------------------------------------------------------
    -0.24
    åħ³åı£
    -0.24
    åıĭ们
    -0.24
    èĨº
    -0.24
    POSITIVE LOGITS
    è·Ŀ
    0.28
    å¦ŀ
    0.27
    underline
    0.26
     kinetic
    0.26
    IVER
    0.25
    itos
    0.24
     memberships
    0.23
    ä¼°
    0.23
     membership
    0.23
     Liv
    0.23
    Activations Density 2.279%

    No Known Activations

    This feature has no known activations.