© 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. 7009
    Prev
    Next
    INDEX
    Explanations

    common, widespread

    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
    inals
    -0.28
    gebung
    -0.25
    åħħ足çļĦ
    -0.25
    è¿İ
    -0.24
     specimens
    -0.24
    åħħ足
    -0.24
    使ä¹ĭ
    -0.23
     specimen
    -0.23
    loth
    -0.23
    itals
    -0.23
    POSITIVE LOGITS
    gest
    0.26
    EEK
    0.26
    gle
    0.26
    CADE
    0.24
     Mex
    0.23
    ban
    0.23
     kat
    0.23
    SCO
    0.23
     mex
    0.23
    gence
    0.23
    Activations Density 1.848%

    No Known Activations