© 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. 30028
    Prev
    Next
    INDEX
    Explanations

    Texas

    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
    apor
    -0.28
    æµģ
    -0.28
    arged
    -0.28
    tf
    -0.26
    ACC
    -0.25
    åı¼
    -0.25
     flow
    -0.25
    æµģ转
    -0.24
    äºĨå¤ļå°ij
    -0.24
    t
    -0.24
    POSITIVE LOGITS
    åIJĮæŃ¥
    0.28
    ==$
    0.26
    uploads
    0.26
    bish
    0.25
    ubb
    0.25
    æĺ¼
    0.25
    çļĦéģĵè·¯
    0.25
    —but
    0.24
    DDD
    0.24
    缩çŁŃ
    0.24
    Activations Density 0.325%

    No Known Activations