© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20504
    Prev
    Next
    INDEX
    Explanations

    make, enhance, provide, bring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ìĿ´ëĿ¼ë©°
    -0.06
    ode
    -0.05
    籤
    -0.05
    为åħ¶
    -0.05
    åĪĹåħ¥
    -0.05
    üst
    -0.05
    odo
    -0.05
     tant
    -0.05
    éģ¿åħįåĽł
    -0.05
    quat
    -0.05
    POSITIVE LOGITS
    itas
    0.06
    faf
    0.06
    غÙĪ
    0.06
     presid
    0.06
    交å¾ħ
    0.06
    strcasecmp
    0.06
     efectiv
    0.06
    ologo
    0.06
    交代
    0.06
    stitusi
    0.06
    Activations Density 0.006%

    No Known Activations