© 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. 20309
    Prev
    Next
    INDEX
    Explanations

    as well

    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
    ically
    -0.07
    ik
    -0.06
    en
    -0.06
    ably
    -0.06
    å°Ĩä»ĸ
    -0.06
    umer
    -0.06
    uous
    -0.06
     accordance
    -0.06
    ikut
    -0.05
    èĩªå·±åİ»
    -0.05
    POSITIVE LOGITS
    /OR
    0.08
    мееÑĤÑģÑı
    0.06
    lei
    0.05
    é¤IJ
    0.05
     estructur
    0.05
    ATAL
    0.05
    åĴĮç»´çĶŁç´ł
    0.05
    dır
    0.05
    ÙĪجد
    0.05
    troppo
    0.05
    Activations Density 0.016%

    No Known Activations