© 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. 23-TRANSCODER-HP
    7. 24569
    Prev
    Next
    INDEX
    Explanations

    online content

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     dah
    -0.29
     Not
    -0.29
    (reader
    -0.26
     aio
    -0.25
    Not
    -0.25
    读èĢħ
    -0.25
    .reader
    -0.25
     Fam
    -0.25
     reader
    -0.25
    raph
    -0.25
    POSITIVE LOGITS
     principals
    0.31
    æīĢåģļçļĦ
    0.30
    ileo
    0.29
    åģļçļĦ
    0.28
    uche
    0.27
    å±Ģéĥ¨
    0.27
    Ψ
    0.27
    _epsilon
    0.26
    hma
    0.26
    èĢģ人家
    0.26
    Activations Density 0.003%

    No Known Activations