© 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. 21872
    Prev
    Next
    INDEX
    Explanations

    up to you to decide

    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
    ako
    -0.06
    ол
    -0.06
    uter
    -0.05
    eh
    -0.05
    æĺ¯åĶ¯ä¸Ģ
    -0.05
    eto
    -0.05
    ehr
    -0.05
    no
    -0.05
    wine
    -0.05
     loco
    -0.05
    POSITIVE LOGITS
     polec
    0.06
    enius
    0.06
    licht
    0.06
    kst
    0.06
     achar
    0.06
    解éļ¾
    0.06
     suss
    0.05
    èĶ¼
    0.05
    æ±²
    0.05
    PUT
    0.05
    Activations Density 0.006%

    No Known Activations