© 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. 24981
    Prev
    Next
    INDEX
    Explanations

    answer

    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
    -insert
    -0.29
    /uploads
    -0.27
    .squareup
    -0.27
    以ä¸ĬçļĦ
    -0.24
    æİ°
    -0.24
     McKenzie
    -0.24
    UIS
    -0.24
    Inserted
    -0.24
    ioned
    -0.24
    GI
    -0.23
    POSITIVE LOGITS
    athing
    0.27
    sec
    0.26
     key
    0.26
    OWER
    0.25
    ines
    0.24
     securities
    0.24
    ing
    0.24
    m
    0.24
    azo
    0.24
     pair
    0.23
    Activations Density 0.012%

    No Known Activations