© 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. 12-TRANSCODER-HP
    7. 22696
    Prev
    Next
    INDEX
    Explanations

    us

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ought
    -0.28
    æĺ¼å¤ľ
    -0.27
    eterangan
    -0.27
     "{"
    -0.25
    æĸ°çĶŁ
    -0.24
    apeut
    -0.24
     ActiveSupport
    -0.24
     '{}
    -0.24
     budgets
    -0.24
    BOT
    -0.23
    POSITIVE LOGITS
    广åijĬæľįåĬ¡
    0.26
    ç³Ļ
    0.25
     Hundred
    0.25
    读åIJİ
    0.24
    好åIJĹ
    0.24
    è¶ħ级
    0.24
    ually
    0.24
    lesi
    0.23
     stationary
    0.23
    å¥ij
    0.23
    Activations Density 0.010%

    No Known Activations