© 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. 23193
    Prev
    Next
    INDEX
    Explanations

    reproduce

    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
    obbled
    -0.28
    qid
    -0.25
    éĿŀ常å¤ļ
    -0.25
    ksam
    -0.24
     ATI
    -0.24
    claimer
    -0.24
     pudd
    -0.24
    cec
    -0.24
    aced
    -0.24
     Ride
    -0.23
    POSITIVE LOGITS
    æĺ¯å¯¹
    0.30
    glob
    0.28
     crate
    0.27
    继
    0.26
    ä½ľé£İ
    0.26
     glob
    0.25
    èĢħ
    0.25
    缸
    0.24
    UTF
    0.24
    ç®į
    0.24
    Activations Density 0.012%

    No Known Activations