© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 25435
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .Absolute
    -0.29
    ioned
    -0.27
    ä½łçľĭ
    -0.26
     challenge
    -0.26
    FI
    -0.25
     es
    -0.25
    解åĨ³éĹ®é¢ĺ
    -0.24
    :absolute
    -0.24
    fi
    -0.24
    ead
    -0.24
    POSITIVE LOGITS
    igsaw
    0.28
    ç³»
    0.27
    wel
    0.25
    æĶ¯çº¿
    0.25
    ODO
    0.24
    duk
    0.24
     unl
    0.24
    webtoken
    0.24
    æ©ĩ
    0.24
     Cros
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.