© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20908
    Prev
    Next
    INDEX
    Explanations

    if not

    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
    skom
    -0.07
    åı¤å±ĭ
    -0.07
    ügen
    -0.07
    arate
    -0.07
     mẽ
    -0.07
    aises
    -0.07
    lais
    -0.06
    emps
    -0.06
    avond
    -0.06
    度ãģª
    -0.06
    POSITIVE LOGITS
    otta
    0.05
    i
    0.05
    å§ĵ
    0.05
    (optional
    0.05
    _
    0.05
    ê´Ģ
    0.05
    ’t
    0.05
     qu
    0.05
    -
    0.05
    æĺ¯ä¸įæĺ¯
    0.05
    Activations Density 0.005%

    No Known Activations