© 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. 63939
    Prev
    Next
    INDEX
    Explanations

    natural language text

    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
    chied
    -0.27
    ypad
    -0.26
     saja
    -0.25
    èĴĻ
    -0.24
    eurs
    -0.24
    adia
    -0.24
    åıijå¸ĥåħ¬åijĬ
    -0.24
    cline
    -0.23
    (||
    -0.23
     feeder
    -0.23
    POSITIVE LOGITS
    AndGet
    0.28
    among
    0.27
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.27
    ä¸Ģå®ļæĺ¯
    0.26
    Instagram
    0.25
    女è£ħ
    0.25
     ấy
    0.25
    intColor
    0.25
     invariably
    0.24
     jes
    0.24
    Activations Density 57.066%

    No Known Activations