© 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. 22992
    Prev
    Next
    INDEX
    Explanations

    Engineering/Physics

    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
     stretch
    -0.26
    ãģ¡ãģª
    -0.26
     denim
    -0.26
    Advertis
    -0.25
     avis
    -0.25
    åĽŀäºĭ
    -0.25
    对çĿĢ
    -0.25
    æĪIJéķ¿ä¸º
    -0.24
     assembly
    -0.24
    .snp
    -0.24
    POSITIVE LOGITS
    æĬķ
    0.26
    æĬķåħ¥
    0.25
    SED
    0.25
    åį·
    0.24
     Pine
    0.24
    umba
    0.24
    ACC
    0.24
    éĺ³åħī
    0.24
    ropical
    0.23
     Concent
    0.23
    Activations Density 0.002%

    No Known Activations