© 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. 21181
    Prev
    Next
    INDEX
    Explanations

    nouns followed by specific words/punctuation

    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
    éĢļ常为
    -0.05
     Chapman
    -0.05
    asanya
    -0.05
     sog
    -0.05
    ix
    -0.05
    éĢļ常éľĢè¦ģ
    -0.05
    è¦ģå¦Ĥä½ķ
    -0.05
     tÃł
    -0.05
     tatt
    -0.05
    icity
    -0.05
    POSITIVE LOGITS
    æ¼ı
    0.06
    atte
    0.05
    agine
    0.05
    openhagen
    0.05
    èĵĦ
    0.05
    akk
    0.05
     Ngh
    0.05
    ills
    0.05
    ä»»ä½ķæŶåĢĻ
    0.05
    eszcze
    0.05
    Activations Density 0.019%

    No Known Activations