© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7218
    Prev
    Next
    INDEX
    Explanations

    Informal, conversational writing

    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
     purposely
    -0.31
    æķħæĦı
    -0.30
    æľīåĪ©äºİ
    -0.28
    è¿İåIJĪ
    -0.28
    éªĹ
    -0.28
    为äºĨ让
    -0.27
    åĢŁæѤ
    -0.27
    åĢŁåĬ©
    -0.27
    诱åıij
    -0.27
    åĬ¨æľº
    -0.26
    POSITIVE LOGITS
     Suff
    0.28
     Handling
    0.28
     ADDRESS
    0.27
    elter
    0.27
    umbo
    0.27
     handling
    0.26
    .handleError
    0.26
     handle
    0.26
     address
    0.26
     Pale
    0.26
    Activations Density 0.134%

    No Known Activations