© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22443
    Prev
    Next
    INDEX
    Explanations

    hyphen-preceded words or codes

    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
    Negative Logits
    æĤī
    -0.05
    è¹
    -0.05
     alike
    -0.05
     hands
    -0.05
    icit
    -0.05
    æľ¬ç¯ĩ
    -0.05
     paradigm
    -0.05
     overt
    -0.04
    ime
    -0.04
    t
    -0.04
    POSITIVE LOGITS
    éĿŀ
    0.07
    utile
    0.06
    änz
    0.06
    éĿŀå¿ħè¦ģ
    0.06
    ror
    0.06
    æĺ¯éĿŀ
    0.06
    chluss
    0.06
    hoek
    0.06
    çī©æµģæľīéĻIJåħ¬åı¸
    0.06
     esfuer
    0.06
    Activations Density 0.043%

    No Known Activations