© 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. 32-TRANSCODER-HP
    7. 43537
    Prev
    Next
    INDEX
    Explanations

    Direct address, conversational

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ground
    -0.30
    orgia
    -0.27
    theless
    -0.26
    afx
    -0.26
    bies
    -0.26
    æ³¼
    -0.25
    ceb
    -0.25
    ilitation
    -0.25
     eup
    -0.25
    езд
    -0.25
    POSITIVE LOGITS
     ever
    0.36
    åºĶ该
    0.33
     should
    0.31
     Should
    0.31
    éĥ½åºĶ该
    0.28
    .should
    0.28
     EVER
    0.28
    æĩī該
    0.28
    should
    0.28
     Ever
    0.28
    Activations Density 0.012%

    No Known Activations