© 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. 22-TRANSCODER-HP
    7. 97440
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ackle
    -0.27
    isel
    -0.25
     trickle
    -0.25
    å¼ĤæĢ§
    -0.25
    ominated
    -0.25
    娣
    -0.24
    isis
    -0.24
    .interface
    -0.24
     shaken
    -0.24
     Admir
    -0.23
    POSITIVE LOGITS
    åħ¶å®ĥéĹ®é¢ĺ
    0.27
     Ware
    0.25
    rol
    0.25
    è¿ĺæľīä¸ĢäºĽ
    0.24
     Others
    0.24
    ullah
    0.24
    æĬ¬èµ·
    0.24
    sbin
    0.23
    (statement
    0.23
    protect
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.