© 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. 21372
    Prev
    Next
    INDEX
    Explanations

    common separators and version

    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
    æĸ°å¤©åľ°
    -0.06
    اء
    -0.06
    _='
    -0.06
    [âĢ¦
    -0.05
    èĥľ
    -0.05
    å®īåħ¨äºĭæķħ
    -0.05
    ubi
    -0.05
     addition
    -0.05
     [âĢ¦
    -0.05
    .ca
    -0.05
    POSITIVE LOGITS
    ↵
    0.07
    å¥ij
    0.06
    edge
    0.06
    Edge
    0.06
    moc
    0.05
    åıįæŃ£
    0.05
    елÑĮ
    0.05
     ÐŁÐ»ÑİÑģ
    0.05
    ynch
    0.05
    æĥ³ä½ł
    0.05
    Activations Density 0.251%

    No Known Activations