© 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. 21046
    Prev
    Next
    INDEX
    Explanations

    given

    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
    2
    -0.05
    è¾¾
    -0.05
    er
    -0.05
    ê°ģ
    -0.05
    3
    -0.05
    ian
    -0.05
     famous
    -0.05
    in
    -0.05
     from
    -0.05
    ure
    -0.05
    POSITIVE LOGITS
     allotted
    0.07
    enspiel
    0.07
    stell
    0.07
     sÃłng
    0.07
    æĺ¯çĶ¨æĿ¥
    0.07
    ียà¹Į
    0.06
    olitik
    0.06
    cheng
    0.06
     tá»ĵi
    0.06
    azon
    0.06
    Activations Density 0.024%

    No Known Activations