© 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. 9-TRANSCODER-HP
    7. 30033
    Prev
    Next
    INDEX
    Explanations

    stick

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_9.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.9.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lest
    -0.27
     klar
    -0.26
     transcript
    -0.26
    -navbar
    -0.24
    avor
    -0.24
    hip
    -0.24
    melon
    -0.24
    bcc
    -0.23
    éĿŀ常åĸľæ¬¢
    -0.23
    trä
    -0.23
    POSITIVE LOGITS
    uffs
    0.28
    褥
    0.27
    æIJ´
    0.26
    æĴ¬
    0.26
    åĸĺ
    0.26
    æģ¯æģ¯
    0.25
    escal
    0.24
    gL
    0.24
    å½ĵåľº
    0.24
    çīį
    0.23
    Activations Density 19.429%

    No Known Activations