© 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. 129785
    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
    ilters
    -0.27
    wins
    -0.25
    oui
    -0.25
    .si
    -0.24
     preco
    -0.24
    ä¸Ģ个
    -0.24
    ilm
    -0.23
    åĩłæ¬¡
    -0.23
     alm
    -0.23
    ilitation
    -0.23
    POSITIVE LOGITS
    vier
    0.29
    çݩ家æĿ¥è¯´
    0.27
     embar
    0.25
    ä¸įæĸ¹ä¾¿
    0.24
    eut
    0.23
    ató
    0.23
    åľ¨å¤ĸéĿ¢
    0.23
    æĭĹ
    0.23
    ÑĤеÑħ
    0.23
    igar
    0.23
    Activations Density 0.033%

    No Known Activations

    This feature has no known activations.