© 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. 27-TRANSCODER-HP
    7. 9442
    Prev
    Next
    INDEX
    Explanations

    Business and project management

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    _globals
    -0.28
     dashes
    -0.27
     opaque
    -0.24
    ducted
    -0.24
    .singleton
    -0.23
    æį¢äºĨ
    -0.23
     turret
    -0.23
    Spaces
    -0.23
    ä½ĵ
    -0.23
    umeric
    -0.23
    POSITIVE LOGITS
     acad
    0.30
    geist
    0.27
     tourism
    0.26
    ä½ľä¸ºä¸Ģç§į
    0.26
     politics
    0.26
    ä½ľä¸º
    0.26
    lopedia
    0.26
     termin
    0.26
     Incident
    0.26
     theory
    0.25
    Activations Density 0.006%

    No Known Activations