© 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. 17154
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     Bro
    -0.05
    NO
    -0.05
    éģ
    -0.05
    è²Į
    -0.05
     bro
    -0.05
    No
    -0.05
    bro
    -0.05
     widely
    -0.05
     outr
    -0.05
    å¹¿æ³Ľ
    -0.05
    POSITIVE LOGITS
    为己
    0.06
    ecca
    0.06
    omatic
    0.06
    éĥ½åIJĪ
    0.06
    éĽģå¡Ķ
    0.06
    HttpStatus
    0.06
     Sociales
    0.06
    OMATIC
    0.06
    boarding
    0.06
    ÒĽÐ¸
    0.06
    Activations Density 0.000%

    No Known Activations