© 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. 29876
    Prev
    Next
    INDEX
    Explanations

    legal documents

    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
    ØŃÙģ
    -0.26
    å·²å®ĮæĪIJ
    -0.25
    _failed
    -0.25
    иÑĨÑĭ
    -0.25
    agnost
    -0.25
    çĶŁäº§çº¿
    -0.24
    reas
    -0.24
    udeau
    -0.24
    мел
    -0.24
     butcher
    -0.24
    POSITIVE LOGITS
    .bo
    0.27
    apo
    0.27
    åĪĿ级
    0.26
    çļĦæĶ¿æ²»
    0.25
    æ°´ä¸Ĭ
    0.25
    è§īéĨĴ
    0.25
    unders
    0.24
    çĸ°
    0.24
    强çĥĪçļĦ
    0.24
    åºķå±Ĥ
    0.24
    Activations Density 10.897%

    No Known Activations