© 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. 19-TRANSCODER-HP
    7. 8049
    Prev
    Next
    INDEX
    Explanations

    development

    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
    çļ´
    -0.25
    次ä¼ļè®®
    -0.24
    CTION
    -0.24
    enk
    -0.24
    dı
    -0.24
     пÑıÑĤ
    -0.24
    csv
    -0.23
    å¢ŀåĬłäºĨ
    -0.23
    ighter
    -0.23
    erta
    -0.23
    POSITIVE LOGITS
    ivalent
    0.31
     Origin
    0.28
    amodel
    0.27
     deter
    0.26
    åijĹ
    0.26
     acomp
    0.25
    å§ĵåIJį
    0.25
    >Last
    0.25
    bole
    0.25
    åħ¨éĿ¢
    0.24
    Activations Density 0.885%

    No Known Activations