© 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. 23147
    Prev
    Next
    INDEX
    Explanations

    recognize

    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
    utra
    -0.27
    CHED
    -0.27
    ROTO
    -0.25
     glands
    -0.25
     inclination
    -0.25
    ãģ¼
    -0.25
     jes
    -0.25
    èī¯å¥½çļĦ
    -0.24
     BRO
    -0.24
    gly
    -0.24
    POSITIVE LOGITS
    atable
    0.28
    ioned
    0.26
    çļĦçĶŁæ´»
    0.26
    æĪ¿ç§Ł
    0.25
    ain
    0.25
    ä½ĵ
    0.25
    assing
    0.25
    _CONST
    0.25
     truncate
    0.24
    ains
    0.24
    Activations Density 0.001%

    No Known Activations