© 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. 23-TRANSCODER-HP
    7. 24053
    Prev
    Next
    INDEX
    Explanations

    Technical and research writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    表çİ°
    -0.28
    Performance
    -0.26
    lobal
    -0.26
    çļĦåį±å®³
    -0.26
    ÑĥÑģÑĤ
    -0.26
     Performance
    -0.25
    çļĦ表çİ°
    -0.25
    表çı¾
    -0.25
    çݰ象
    -0.24
    LOC
    -0.24
    POSITIVE LOGITS
     diet
    0.34
    第ä¸Ģ家
    0.33
     diets
    0.30
    diet
    0.30
    é¥®é£Ł
    0.29
    æݥ触åĪ°
    0.29
     dietary
    0.29
     differed
    0.28
     histories
    0.27
    æĥħå¢ĥ
    0.27
    Activations Density 0.002%

    No Known Activations