© 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. 25-TRANSCODER-HP
    7. 108712
    Prev
    Next
    INDEX
    Explanations

    Male names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     imports
    -0.27
     Imported
    -0.26
    opath
    -0.26
    绣çŃ¹
    -0.25
     Provid
    -0.25
     Jud
    -0.25
    -depend
    -0.25
    èĴĻ
    -0.24
    <TreeNode
    -0.24
     Tap
    -0.24
    POSITIVE LOGITS
    iliar
    0.31
    dataType
    0.28
    ILED
    0.26
     Willis
    0.26
    |array
    0.25
    Enumerable
    0.24
    yre
    0.24
    ãģĨãģ¡ãģ«
    0.24
    èīĩ
    0.24
    ertz
    0.24
    Activations Density 0.934%

    No Known Activations