© 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. 16581
    Prev
    Next
    INDEX
    Explanations

    plus, followed by punctuation or "size"

    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
    ulen
    -0.08
    бÑĥдÑĮÑĤе
    -0.07
    ت
    -0.07
    ic
    -0.06
    ex
    -0.06
    aining
    -0.06
    t
    -0.06
    ti
    -0.06
    orical
    -0.06
    eh
    -0.06
    POSITIVE LOGITS
    er
    0.10
    erne
    0.08
    eranno
    0.08
    ê¸Ī
    0.07
    itude
    0.07
    erings
    0.07
    erer
    0.07
    erad
    0.06
    erche
    0.06
    ment
    0.06
    Activations Density 0.009%

    No Known Activations