© 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. 150073
    Prev
    Next
    INDEX
    Explanations

    the

    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
    å¼ł
    -0.42
    æĿİ
    -0.40
    éĻĪ
    -0.35
     Mr
    -0.35
    åĪĺ
    -0.34
     James
    -0.33
    å¼µ
    -0.33
     Gerard
    -0.33
     William
    -0.32
     Joseph
    -0.32
    POSITIVE LOGITS
    know
    0.26
     Inject
    0.25
    _known
    0.24
     Freak
    0.24
    inject
    0.24
    åıªçŁ¥éģĵ
    0.24
     Yale
    0.24
     titular
    0.23
    onom
    0.23
     acts
    0.23
    Activations Density 1.272%

    No Known Activations