© 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. 29823
    Prev
    Next
    INDEX
    Explanations

    code

    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
    ÑĢÑĥÑĩ
    -0.30
    éĻ¢éĻ¢éķ¿
    -0.27
    urved
    -0.26
    æĥ¡
    -0.26
    ewed
    -0.26
    æģ¶
    -0.26
     Roof
    -0.26
    urve
    -0.25
    åIJĮç±»
    -0.25
    resents
    -0.24
    POSITIVE LOGITS
    ora
    0.29
    icom
    0.28
    orra
    0.27
    å®ī
    0.27
     unchanged
    0.26
     somewhere
    0.26
    oh
    0.25
    oft
    0.25
    é¢ijçİĩ
    0.24
    olog
    0.24
    Activations Density 0.187%

    No Known Activations