© 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. 6733
    Prev
    Next
    INDEX
    Explanations

    parents

    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
    ниÑĨ
    -0.29
    åĬ¨äºº
    -0.26
    æ·ĭ
    -0.25
    ilha
    -0.25
     when
    -0.25
    ascade
    -0.25
    åı®
    -0.25
    tingham
    -0.25
    ower
    -0.24
     casc
    -0.24
    POSITIVE LOGITS
    ensch
    0.30
    AsStream
    0.29
    resco
    0.27
    å±Ģå±Ģéķ¿
    0.26
    éĿ¢ä¸´çļĦ
    0.26
    Streams
    0.25
    å±Ģåī¯å±Ģéķ¿
    0.25
    å±Ģ
    0.25
    éĥ¨
    0.24
    æŃ¥
    0.24
    Activations Density 0.793%

    No Known Activations