© 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. 24-TRANSCODER-HP
    7. 150121
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ¯ı个人çļĦ
    -0.27
    åħĴ
    -0.26
    è¦ģåĿļæĮģ
    -0.25
    _heap
    -0.24
    LONG
    -0.24
    íı°
    -0.24
    éŃļ
    -0.23
    jiang
    -0.23
    ingly
    -0.23
    uet
    -0.23
    POSITIVE LOGITS
    çIJ¦
    0.25
     distinction
    0.25
     Princip
    0.25
     SECRET
    0.24
     sure
    0.23
     tus
    0.23
    ozy
    0.23
    æĹ»
    0.23
     realized
    0.23
     separ
    0.23
    Activations Density 1.518%

    No Known Activations

    This feature has no known activations.