© 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. 20-TRANSCODER-HP
    7. 141218
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸įåħģ许
    -0.28
    NotAllowed
    -0.27
    没æĶ¶
    -0.26
    ErrorException
    -0.26
    amb
    -0.25
    éī´åĪ«
    -0.25
    ä¸įäºĪ
    -0.25
    çĩ¥
    -0.25
    é»ijåIJįåįķ
    -0.25
    äh
    -0.24
    POSITIVE LOGITS
    assage
    0.26
    (pm
    0.26
    "display
    0.26
    ä¸ĢæŃ¥æŃ¥
    0.25
    xAC
    0.25
    xcd
    0.25
    PRETTY
    0.25
    å®Įæķ´çļĦ
    0.25
    ()._
    0.25
    ollywood
    0.25
    Activations Density 10.067%

    No Known Activations