© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22527
    Prev
    Next
    INDEX
    Explanations

    by followed by a number or specific word

    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
    Negative Logits
    uko
    -0.06
    n
    -0.05
    icu
    -0.05
    as
    -0.05
    ALTH
    -0.05
    elh
    -0.05
    fe
    -0.05
     chunks
    -0.05
    çĻ½èıľ
    -0.05
    бай
    -0.05
    POSITIVE LOGITS
    rightness
    0.06
    angler
    0.06
    è¯ģ
    0.06
    èŃī
    0.06
    ÑĢÑĬ
    0.06
    ivot
    0.06
     пÑĢавоÑģ
    0.05
    -done
    0.05
    ingham
    0.05
    RAFT
    0.05
    Activations Density 0.014%

    No Known Activations