© 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. 29691
    Prev
    Next
    INDEX
    Explanations

    mechanical

    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
    èį¡
    -0.29
    è°ģçŁ¥éģĵ
    -0.27
    )”
    -0.27
    å¦Ĥ
    -0.26
    arkan
    -0.26
    CUS
    -0.26
    iya
    -0.24
    isches
    -0.23
     (“
    -0.23
    èĬŃ
    -0.23
    POSITIVE LOGITS
     dép
    0.30
    oler
    0.29
    è¶³å¤ŁçļĦ
    0.28
    è¶³å¤Ł
    0.28
     myself
    0.27
    轸
    0.26
     suffice
    0.25
     flo
    0.24
    æľ¬ç«Ļ
    0.24
     Icon
    0.24
    Activations Density 0.812%

    No Known Activations