© 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. 96301
    Prev
    Next
    INDEX
    Explanations

    Names and locations

    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
     powers
    -0.30
    arks
    -0.28
     black
    -0.27
    交
    -0.27
     exp
    -0.25
     Lange
    -0.25
    fsp
    -0.25
     bundles
    -0.25
     fed
    -0.25
     expos
    -0.25
    POSITIVE LOGITS
    atak
    0.30
    guards
    0.28
     شاÙħÙĦ
    0.26
    EGA
    0.26
     recurring
    0.25
     Gratuit
    0.25
     doorstep
    0.25
    egas
    0.24
     Companion
    0.24
     Guard
    0.24
    Activations Density 0.000%

    No Known Activations