© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21641
    Prev
    Next
    INDEX
    Explanations

    find something

    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
     "
    -0.06
    /
    -0.06
     “
    -0.05
    论
    -0.05
    èĬ
    -0.05
    “
    -0.05
    tons
    -0.05
    好åĥı
    -0.05
    æĸ¹
    -0.05
     '
    -0.05
    POSITIVE LOGITS
    ingkatan
    0.09
    åĬłæĭ¿å¤§
    0.08
    variably
    0.08
    åĽ½å®¶åĴĮåľ°åĮºçļĦ
    0.07
    edir
    0.07
     Vesti
    0.07
    estu
    0.07
    опо
    0.07
    è¿ĻéĩĮéĥ½æľī
    0.07
    kadang
    0.07
    Activations Density 0.051%

    No Known Activations