© 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
    2. Qwen3-4B
    3. 30-TRANSCODER-HP
    4. 96369
    Prev
    Next
    INDEX
    Explanations

    article

    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
     Found
    -0.27
    ificent
    -0.27
    coe
    -0.25
    oshi
    -0.24
    illard
    -0.24
     all
    -0.24
    ä¼ģä¸ļåĴĮ
    -0.23
    PRESSION
    -0.23
    çĿ«
    -0.23
    è´§å¸ģ
    -0.23
    POSITIVE LOGITS
     subt
    0.28
    _subtype
    0.28
    çķĻä¸ĭ
    0.27
     COURT
    0.26
    igne
    0.26
     hé
    0.25
    ļ
    0.25
    acf
    0.24
    Americ
    0.24
     contiene
    0.24
    Activations Density 0.109%

    No Known Activations