© 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. 18-TRANSCODER-HP
    7. 89690
    Prev
    Next
    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    peria
    -0.29
     coer
    -0.26
    uates
    -0.26
    头ä¸Ĭ
    -0.25
    åijµ
    -0.24
    oron
    -0.24
    дÑĥм
    -0.24
     contests
    -0.24
    uron
    -0.24
    peri
    -0.24
    POSITIVE LOGITS
    SEM
    0.30
     SEM
    0.28
    ç«Ł
    0.26
    etten
    0.26
    çªį
    0.26
    ?>č↵č↵
    0.25
    èĪįä¸įå¾Ĺ
    0.24
    .ObjectModel
    0.24
    éĩİ
    0.24
    lit
    0.23
    Activations Density 3.603%

    No Known Activations