© 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. 19013
    Prev
    Next
    INDEX
    Explanations

    lengths and limits

    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
    keiten
    -0.07
     ìĿ¸íķ´
    -0.07
    onet
    -0.06
    oby
    -0.06
    atian
    -0.06
    izontal
    -0.06
    celli
    -0.06
    Äįaj
    -0.06
    atings
    -0.06
    ulatory
    -0.06
    POSITIVE LOGITS
    wiÅĽcie
    0.07
    reas
    0.06
    ments
    0.06
     Hause
    0.06
    enticate
    0.06
    aneo
    0.06
    uated
    0.06
    wise
    0.06
    ting
    0.06
    ti
    0.06
    Activations Density 0.016%

    No Known Activations