© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 31758
    Prev
    Next
    INDEX
    Explanations

    Demeter, junction, flag, effects, bias, selection

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    chy
    -0.06
    obile
    -0.06
    utes
    -0.06
    åįĥç§ĭ
    -0.06
    æĸ¼
    -0.06
    ifax
    -0.06
    泪
    -0.06
    å¢ħ
    -0.06
    nt
    -0.05
    .recycle
    -0.05
    POSITIVE LOGITS
    êu
    0.09
    eret
    0.09
    bacher
    0.09
    utr
    0.08
    audi
    0.07
     licenci
    0.07
    óf
    0.07
    å§Ĩæĸ¯
    0.07
    åį´æľī
    0.07
    adol
    0.07
    Activations Density 0.036%

    No Known Activations