© 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. 96266
    Prev
    Next
    INDEX
    Explanations

    rob

    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
    æĮ½
    -0.28
    主人
    -0.27
    æĵį
    -0.27
    andler
    -0.26
    è¶ħæłĩ
    -0.26
    ALAR
    -0.25
    ustry
    -0.24
    å°º
    -0.24
    uç
    -0.24
    lor
    -0.23
    POSITIVE LOGITS
    dea
    0.33
    de
    0.31
    dee
    0.30
     incidental
    0.28
    Structure
    0.28
    elia
    0.27
    breadcrumb
    0.27
    ISIBLE
    0.26
    æ·±å±Ĥ
    0.25
     Ult
    0.25
    Activations Density 0.003%

    No Known Activations