© 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. 9-TRANSCODER-HP
    7. 30059
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĻĢ
    -0.26
     CommandType
    -0.26
     addAction
    -0.25
    DeltaTime
    -0.25
    MISSION
    -0.24
     Laden
    -0.24
    imiters
    -0.24
     Ñıн
    -0.23
    峡
    -0.23
    rogen
    -0.23
    POSITIVE LOGITS
    Scr
    0.27
    alk
    0.25
    sei
    0.25
    æĸ¯åŁº
    0.25
    åŃ©
    0.24
    FLAGS
    0.24
     t
    0.24
    æ¦Ĥè¿°
    0.23
     zeal
    0.23
    åħ¨éĿ¢
    0.23
    Activations Density 0.225%

    No Known Activations