© 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. 23-TRANSCODER-HP
    7. 24682
    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
    Not in Any Lists

    No Comments

    Negative Logits
    andon
    -0.30
    ANC
    -0.28
    çĶµåŃIJ
    -0.27
    ä¾į
    -0.26
    affen
    -0.26
    èijĹ
    -0.26
    éĤ¦
    -0.26
    -fi
    -0.26
    emarks
    -0.25
    ierce
    -0.25
    POSITIVE LOGITS
     He
    0.29
    åIJįå½ķ
    0.27
     Ho
    0.27
     ha
    0.26
     out
    0.26
     Ca
    0.26
     qu
    0.25
     hem
    0.25
     Sh
    0.25
     Ry
    0.25
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.