© 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. 95304
    Prev
    Next
    INDEX
    Explanations

    Code/URLs

    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
    -toggle
    -0.28
    å¼¹
    -0.28
     Command
    -0.28
     Pars
    -0.28
     beg
    -0.27
    hare
    -0.27
    pars
    -0.27
     intern
    -0.26
    ystem
    -0.26
     paras
    -0.26
    POSITIVE LOGITS
    èĩªçĶ±
    0.29
    nqu
    0.29
    iative
    0.29
    nda
    0.28
    æ³ģ
    0.27
    é½IJ
    0.26
    éģĴ
    0.26
    IEW
    0.26
    VEC
    0.26
    æĶ¾æīĭ
    0.25
    Activations Density 0.930%

    No Known Activations