© 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. 8928
    Prev
    Next
    INDEX
    Explanations

    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
     rub
    -0.27
     offices
    -0.26
     Portions
    -0.25
    fried
    -0.24
    åIJĪä½ľ
    -0.24
     Rub
    -0.24
    даÑİÑĤ
    -0.24
    å®°
    -0.23
    alic
    -0.23
     Rough
    -0.23
    POSITIVE LOGITS
    éªĢ
    0.28
    ROADCAST
    0.26
    IVA
    0.26
    ivamente
    0.26
    çļĦéģĵçIJĨ
    0.25
    çļĦéĩįè¦ģæĢ§
    0.25
    ä¸Ģ个èģĮä¸ļ
    0.25
    ivol
    0.24
     ivory
    0.24
    åľ¨æĪijçľĭæĿ¥
    0.24
    Activations Density 0.542%

    No Known Activations