© 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. 18448
    Prev
    Next
    INDEX
    Explanations

    occurrences counting

    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
    é¢IJ
    -0.05
    ernal
    -0.05
    °
    -0.05
    à¸Ķี
    -0.05
    åħ´
    -0.05
    è¡£
    -0.05
     Rough
    -0.05
    ipt
    -0.05
    æ³Ĭ
    -0.05
    涨
    -0.05
    POSITIVE LOGITS
    amel
    0.06
    indi
    0.06
    ìļ©
    0.06
    kampf
    0.06
    ugt
    0.06
     أسÙħ
    0.06
    utan
    0.06
    uess
    0.06
    uchia
    0.06
    Ø«ÙħاÙĨ
    0.06
    Activations Density 0.019%

    No Known Activations