© 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. 20454
    Prev
    Next
    INDEX
    Explanations

    top lists of rankings

    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
     abort
    -0.06
     exhaust
    -0.06
     (("
    -0.06
    หมà¸Ķ
    -0.06
    æĽ¾çĶ¨åIJį
    -0.06
    วà¹Īามี
    -0.06
    mares
    -0.06
     exhaustive
    -0.05
    еÑģе
    -0.05
    áĥķáĥĺáĥ¡
    -0.05
    POSITIVE LOGITS
    formed
    0.06
    ä¸įåľ¨ä¹İ
    0.05
     concent
    0.05
     radi
    0.05
    ješ
    0.05
     Fle
    0.05
    åIJĮå¿ĥ
    0.05
    æŨ
    0.05
    vida
    0.05
    asil
    0.05
    Activations Density 0.015%

    No Known Activations