© 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. 95608
    Prev
    Next
    INDEX
    Explanations

    Names

    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
    èĭ¦ç¬ij
    -0.27
    (pref
    -0.26
    max
    -0.25
    çī¹å¾ģ
    -0.25
     ðŁĺī
    -0.25
    ç¦Ĭ
    -0.24
    icho
    -0.24
    uche
    -0.24
    rotate
    -0.24
    æģº
    -0.24
    POSITIVE LOGITS
    wealth
    0.29
     Curso
    0.28
    nels
    0.26
    ä¼ļä¸Ĭ
    0.26
    Pure
    0.26
    éĩį
    0.26
    bul
    0.26
    ç©·
    0.25
    éĴ¢
    0.25
    eb
    0.25
    Activations Density 0.104%

    No Known Activations