© 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. 19913
    Prev
    Next
    INDEX
    Explanations

    occurrences and frequency

    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
    Ñļа
    -0.06
    æĺİçıł
    -0.06
    èī²æĥħ
    -0.06
     Studierende
    -0.05
    èĬĻ
    -0.05
    èĥ¯
    -0.05
    Tot
    -0.05
     prec
    -0.05
    иÑĢа
    -0.05
    Ùİاء
    -0.05
    POSITIVE LOGITS
     gri
    0.06
    çĥĤ
    0.06
    ilen
    0.06
     memor
    0.05
    ÑģÑĤÑĢом
    0.05
    绾ç»İ
    0.05
     commun
    0.05
    iler
    0.05
    æĭŁå®ļ
    0.05
     bana
    0.05
    Activations Density 0.007%

    No Known Activations