© 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. 24-TRANSCODER-HP
    7. 150826
    Prev
    Next
    INDEX
    Explanations

    block

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    gba
    -0.25
    享
    -0.25
    xba
    -0.25
    iram
    -0.25
     nack
    -0.24
    essaging
    -0.24
    çļĦè§Ĵ度
    -0.24
    å¿«
    -0.24
    istique
    -0.24
     treasure
    -0.24
    POSITIVE LOGITS
     Hundred
    0.30
    @foreach
    0.28
     swe
    0.26
    shire
    0.26
     hữu
    0.26
    干货
    0.25
    owe
    0.25
     manip
    0.25
     Rahman
    0.25
     hundred
    0.24
    Activations Density 1.478%

    No Known Activations