© 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. 22315
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èĤ²
    -0.31
    æ±Łå±±
    -0.29
    yps
    -0.28
    çĪ¶åŃIJ
    -0.27
    edics
    -0.26
     há»ı
    -0.26
    ä¹ĭ家
    -0.26
     Age
    -0.25
    ASH
    -0.25
    eneration
    -0.25
    POSITIVE LOGITS
    offee
    0.29
    èĬĴ
    0.28
    æĿ¾
    0.28
    tout
    0.27
    bert
    0.27
    pike
    0.27
    æİĴ
    0.26
    ç±³ç²ī
    0.25
    æķĽ
    0.25
    efs
    0.25
    Activations Density 0.000%

    No Known Activations