© 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. 18870
    Prev
    Next
    INDEX
    Explanations

    questions that

    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
    ucat
    -0.07
    ayakan
    -0.06
    ä½ķåĨµ
    -0.06
    gados
    -0.06
    严éĩįåIJİæŀľ
    -0.06
    renom
    -0.06
    ä¸Ĭè¿°äºĭå®ŀ
    -0.06
    huis
    -0.06
    istra
    -0.06
    pha
    -0.06
    POSITIVE LOGITS
    çļĦéĤ£ç§į
    0.06
    没æľī被
    0.06
     kind
    0.05
     Kind
    0.05
    None
    0.05
    åıĪä¸įæĺ¯
    0.05
    )?
    0.05
     likes
    0.05
    éļ¾éģĵæĺ¯
    0.05
     rather
    0.05
    Activations Density 0.072%

    No Known Activations