© 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. 29919
    Prev
    Next
    INDEX
    Explanations

    print

    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
    åĭĭ
    -0.28
    æľĽ
    -0.27
    asons
    -0.27
    naire
    -0.27
     (%
    -0.27
    æļĩ
    -0.27
    иÑĨе
    -0.26
    oreach
    -0.26
     interviewer
    -0.25
    æľĭ
    -0.25
    POSITIVE LOGITS
    空ä¸Ń
    0.32
     crossorigin
    0.28
    ibold
    0.26
    ä¸Ģéĺµ
    0.26
    	TokenName
    0.26
    {j
    0.25
    niÄĻ
    0.25
     ila
    0.25
    åĽ½éģĵ
    0.25
     verz
    0.24
    Activations Density 1.428%

    No Known Activations