© 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. 21290
    Prev
    Next
    INDEX
    Explanations

    sense of

    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
    aliste
    -0.07
    ä¸įæ¸ħ
    -0.07
    rous
    -0.07
    ساÙħ
    -0.06
    !”.
    -0.06
    ãģŁãĤĭ
    -0.06
    纽
    -0.06
     sat
    -0.06
     spok
    -0.06
    mite
    -0.06
    POSITIVE LOGITS
     T
    0.06
    rop
    0.05
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½åIJĪåIJĮæ³ķ
    0.05
     initial
    0.05
    tä
    0.05
     O
    0.05
    为主ä½ĵ
    0.05
    utt
    0.05
    inta
    0.05
    åģļæ³ķ
    0.05
    Activations Density 0.002%

    No Known Activations