© 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. 18473
    Prev
    Next
    INDEX
    Explanations

    JavaScript event prevention

    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
    nest
    -0.06
    aufen
    -0.06
    nota
    -0.06
    LOSS
    -0.06
    usk
    -0.06
    ubic
    -0.06
    éĢģå¾Ģ
    -0.06
    adelphia
    -0.06
    fertig
    -0.06
    firma
    -0.06
    POSITIVE LOGITS
    ¦
    0.05
     Antarctica
    0.05
    iche
    0.05
    ogene
    0.05
    ç©¿
    0.05
     bisschen
    0.05
    ¾
    0.05
    /or
    0.04
     masturb
    0.04
    æµ·æ°´
    0.04
    Activations Density 0.002%

    No Known Activations