© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19580
    Prev
    Next
    INDEX
    Explanations

    beach

    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
    çĶľç¾İçļĦ
    -0.05
    ek
    -0.05
    ÑģÑĤÑĮ
    -0.05
    ves
    -0.05
    ment
    -0.05
    夷
    -0.05
    rites
    -0.05
    åı¬
    -0.05
    ìĽĥ
    -0.05
     пÑĥзÑĭ
    -0.05
    POSITIVE LOGITS
     &_
    0.07
     autod
    0.07
    ØŃÙĬ
    0.06
    arus
    0.06
    pecia
    0.06
    æĸ°æĿIJæĸĻæľīéĻIJåħ¬åı¸
    0.06
    afari
    0.06
    ash
    0.06
    (&_
    0.06
    y
    0.06
    Activations Density 0.006%

    No Known Activations