© 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. 18410
    Prev
    Next
    INDEX
    Explanations

    cases with "Circuit"

    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
    ÙĬ
    -0.08
     ìĿ¸íķ´
    -0.08
    euse
    -0.07
    ÙĬÙĭا
    -0.07
    minente
    -0.07
    eranno
    -0.07
    adore
    -0.07
    erne
    -0.07
    iante
    -0.07
    enal
    -0.07
    POSITIVE LOGITS
    0.08
    们
    0.07
    åĪ°çļĦ
    0.07
    бÑĥдÑĮÑĤе
    0.06
    bral
    0.05
    ificates
    0.05
    æ¡©
    0.05
    ared
    0.05
    s
    0.05
    ux
    0.05
    Activations Density 0.004%

    No Known Activations