© 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. 21946
    Prev
    Next
    INDEX
    Explanations

    Arabic script and names

    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
     behalf
    -0.06
    ...
    -0.05
    ÑıÑĤÑĮ
    -0.04
    omer
    -0.04
    -
    -0.04
    -0.04
    段æŶéĹ´
    -0.04
    ä¸Ń没æľī
    -0.04
     peng
    -0.04
    nel
    -0.04
    POSITIVE LOGITS
    ì§ĦìĿĺ
    0.07
    á»ĵ
    0.07
    formats
    0.07
    MOTE
    0.07
    ergen
    0.06
    rench
    0.06
    ennie
    0.06
    змо
    0.06
    лÑĮÑīиков
    0.06
    ÅĤos
    0.06
    Activations Density 0.002%

    No Known Activations