© 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. 107525
    Prev
    Next
    INDEX
    Explanations

    does

    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
    éĶ»çĤ¼
    -0.26
    uchen
    -0.25
    }s
    -0.25
    GLenum
    -0.25
    *))
    -0.25
    èľĪ
    -0.25
     Exercise
    -0.24
    htm
    -0.24
     exercising
    -0.24
    åĨ·éĿĻ
    -0.24
    POSITIVE LOGITS
     it
    0.34
     he
    0.31
     alone
    0.30
     to
    0.29
     product
    0.29
     '
    0.28
     dec
    0.28
     inters
    0.26
     I
    0.26
     they
    0.26
    Activations Density 0.925%

    No Known Activations