© 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. 96293
    Prev
    Next
    INDEX
    Explanations

    early or late

    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
    SystemService
    -0.28
    çĪ±ç¾İ
    -0.26
     didFinish
    -0.25
     keer
    -0.25
    (parseInt
    -0.25
    reet
    -0.25
    IDD
    -0.24
    éĶ·
    -0.24
    =nil
    -0.24
    èĦļ
    -0.24
    POSITIVE LOGITS
     Season
    0.33
     season
    0.31
    é²ľ
    0.28
    season
    0.28
    åŃ£èĬĤ
    0.28
     bloom
    0.28
    æĺ¥åŃ£
    0.28
    ëłģ
    0.27
    ç§ĭåŃ£
    0.27
    Season
    0.27
    Activations Density 0.110%

    No Known Activations