© 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. 142151
    Prev
    Next
    INDEX
    Explanations

    dog

    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
    é«ĵ
    -0.27
    ptive
    -0.27
    upon
    -0.25
     lateinit
    -0.25
    _reporting
    -0.23
    ledge
    -0.23
    éĻ©
    -0.23
     Bern
    -0.23
    ese
    -0.23
    tee
    -0.23
    POSITIVE LOGITS
    éĴŀ
    0.26
    fä
    0.25
    ä¸įåı¯èĥ½
    0.25
    æĺ¯ä¸įåı¯èĥ½
    0.25
    ä¸į好
    0.24
     authorization
    0.24
    çĦĻ
    0.24
    é£ı
    0.23
    æ
    0.23
     doub
    0.23
    Activations Density 13.353%

    No Known Activations