© 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. 109181
    Prev
    Next
    INDEX
    Explanations

    Code and URLs

    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
     imm
    -0.28
    /vendors
    -0.28
    OCK
    -0.26
    illy
    -0.25
    ,start
    -0.25
     bio
    -0.24
     thinly
    -0.24
    è®Ń
    -0.24
    RYPT
    -0.24
     pop
    -0.24
    POSITIVE LOGITS
    é»Ħæĺı
    0.30
    Current
    0.27
     nich
    0.27
    æ¯ķä¸ļåIJİ
    0.26
    current
    0.25
    prop
    0.25
    æľĢä½³
    0.25
     Current
    0.25
    ধ
    0.24
    line
    0.24
    Activations Density 1.293%

    No Known Activations