© 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. 30-TRANSCODER-HP
    7. 95678
    Prev
    Next
    INDEX
    Explanations

    help, showing, illustrate

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æİ¨è¿Ł
    -0.28
    æĮ¡ä½ı
    -0.28
    éĺ»æĮ¡
    -0.28
    çŁ³æĿIJ
    -0.27
     zaj
    -0.27
     purch
    -0.27
    neau
    -0.25
    Console
    -0.25
    æݥ触
    -0.25
    ä¸įä½ı
    -0.25
    POSITIVE LOGITS
     help
    0.41
     better
    0.38
    help
    0.37
    帮åĬ©
    0.37
     helped
    0.36
     illustrate
    0.36
     show
    0.35
     illustrated
    0.35
     helps
    0.35
     shows
    0.34
    Activations Density 0.890%

    No Known Activations