© 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. 19762
    Prev
    Next
    INDEX
    Explanations

    et al

    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
    éºĴ
    -0.06
    aż
    -0.06
    arto
    -0.06
    ÄĹl
    -0.06
    itas
    -0.06
    æł¼æĸ¯
    -0.06
    ates
    -0.06
    ä¸įå½Ĵ
    -0.06
    æīĩéŨ
    -0.05
    ÏĨÏĮ
    -0.05
    POSITIVE LOGITS
    åĪĩå®ŀ
    0.05
    å·²åħ¨éĥ¨
    0.05
    essioni
    0.05
    letter
    0.05
    ictured
    0.05
    æĶ¯
    0.05
    emean
    0.05
    abyrin
    0.05
    edar
    0.05
    efined
    0.05
    Activations Density 0.173%

    No Known Activations