© 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. 95965
    Prev
    Next
    INDEX
    Explanations

    habit

    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
    çģŃ
    -0.32
    个交æĺĵ
    -0.26
     crowd
    -0.25
     dwell
    -0.25
     Remarks
    -0.24
     vig
    -0.24
    ç¼´
    -0.24
    ç¿Ĵ
    -0.24
    涨
    -0.24
    aml
    -0.23
    POSITIVE LOGITS
    æīĭä¸Ĭ
    0.28
    bing
    0.28
    antly
    0.27
     shape
    0.27
     involving
    0.27
    åIJĥå¾Ĺ
    0.26
     formation
    0.26
     presente
    0.25
    å½¢å¼ı
    0.25
    éĴı
    0.25
    Activations Density 0.030%

    No Known Activations