© 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. 20-TRANSCODER-HP
    7. 107705
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    鼶ç¢İ
    -0.32
    [][
    -0.29
     Milo
    -0.27
    подоб
    -0.26
     scr
    -0.26
    åĦ¿
    -0.26
     Essentials
    -0.26
    使åij½
    -0.25
    åĨį度
    -0.25
    è¯įæĿ¡
    -0.25
    POSITIVE LOGITS
    æijĬ
    0.27
    INGS
    0.27
     Counter
    0.26
    à¹Ģà¸ļ
    0.25
     pret
    0.25
    cake
    0.25
     HAPP
    0.25
    ifferential
    0.25
    ivities
    0.25
    lav
    0.25
    Activations Density 0.501%

    No Known Activations