© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 4973
    Prev
    Next
    INDEX
    Explanations

    school

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BIT
    -0.31
     Kom
    -0.27
     Rad
    -0.27
    æĿ³
    -0.26
     Boy
    -0.26
     Bris
    -0.25
    á»ģm
    -0.25
    è§Ī
    -0.25
     diary
    -0.25
    Kom
    -0.25
    POSITIVE LOGITS
    ä»Ģä¹Īéĥ½
    0.28
     nominate
    0.27
    :async
    0.26
    оÑģÑĤи
    0.26
     characterize
    0.26
    éĢģå¾Ģ
    0.26
    TS
    0.26
    HING
    0.25
    æľĢ好çļĦ
    0.25
    toHave
    0.24
    Activations Density 0.024%

    No Known Activations