© 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. 20708
    Prev
    Next
    INDEX
    Explanations

    inaccuracy, inefficiency, instability

    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
    tect
    -0.07
    dach
    -0.06
     нами
    -0.06
    ç·Ĵ
    -0.06
    绪
    -0.06
    ity
    -0.06
    orre
    -0.06
    áŀĻ
    -0.06
    wein
    -0.06
    olec
    -0.05
    POSITIVE LOGITS
    venta
    0.08
    ched
    0.08
    em
    0.07
    variably
    0.07
    ild
    0.06
    onna
    0.06
    mehr
    0.06
    att
    0.06
    tra
    0.06
    tras
    0.06
    Activations Density 0.021%

    No Known Activations