© 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. 41557
    Prev
    Next
    INDEX
    Explanations

    fitness and exercise

    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
    åĵį
    -0.26
    éIJĺ
    -0.26
    ë§Ŀ
    -0.25
    ories
    -0.25
    -wrap
    -0.24
    .synthetic
    -0.24
    ÑĦон
    -0.23
    èİł
    -0.23
     Motion
    -0.23
     begr
    -0.23
    POSITIVE LOGITS
    ä½İ
    0.43
     low
    0.37
    (low
    0.36
     Low
    0.33
    _low
    0.31
    low
    0.30
    Low
    0.30
     LOW
    0.30
    .low
    0.30
    å¾Īä½İ
    0.28
    Activations Density 0.001%

    No Known Activations