© 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. 29678
    Prev
    Next
    INDEX
    Explanations

    museum

    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
    ouri
    -0.24
    è¿ĽæŃ¥
    -0.24
    itor
    -0.24
    íı¬
    -0.24
    ential
    -0.24
    iator
    -0.24
    éĤ¸
    -0.23
    åľ¨åŃ¦æł¡
    -0.23
    erture
    -0.23
    inary
    -0.23
    POSITIVE LOGITS
    lop
    0.27
    ãĥŃãĥ¼
    0.27
    çľĭä¸įè§ģ
    0.26
    èĨij
    0.25
    oa
    0.25
    ä¹ĭç±»
    0.25
    Ð¡ÐŁ
    0.25
     SYMBOL
    0.25
    urn
    0.24
     kuk
    0.24
    Activations Density 1.768%

    No Known Activations