© 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. 129472
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    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
    opened
    -0.24
     played
    -0.23
    iken
    -0.23
     leash
    -0.23
    PLAY
    -0.23
     siÄĻ
    -0.23
    åľĮ
    -0.23
    .gr
    -0.22
     Labrador
    -0.22
    avo
    -0.22
    POSITIVE LOGITS
    è·¸
    0.27
    è¿Ļ座åŁİå¸Ĥ
    0.27
    éļıæŶ
    0.26
    éĥijéĩį
    0.25
    çĨµ
    0.25
    deaux
    0.24
    ä¹Łè¢«
    0.24
    éĩįä¸Ń
    0.24
     sauce
    0.24
    è¿Ľå±ķ
    0.23
    Activations Density 0.006%

    No Known Activations