© 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. 19045
    Prev
    Next
    INDEX
    Explanations

    **catalog issued**

    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
    ross
    -0.05
     salvo
    -0.05
    “
    -0.05
    H
    -0.05
     Across
    -0.05
    lla
    -0.05
    ex
    -0.05
    B
    -0.05
    è·¨è¿ĩ
    -0.05
    æļ´éľ²
    -0.05
    POSITIVE LOGITS
    çIJĨæīĢ
    0.06
    anisme
    0.06
    cust
    0.06
    cipt
    0.06
    *pow
    0.06
    acken
    0.06
    uston
    0.06
    ÙĪÙĩا
    0.06
    ustos
    0.06
    zech
    0.06
    Activations Density 0.007%

    No Known Activations