© 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. 20166
    Prev
    Next
    INDEX
    Explanations

    confidence in the

    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
    æ¼ĶçļĦ
    -0.07
    netinet
    -0.06
    çijĻ
    -0.06
    aver
    -0.06
    ç²¾ç»Ĩ
    -0.06
    avat
    -0.06
    деÑĤÑģÑı
    -0.06
    .precision
    -0.06
     disastr
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
    æ¯Ĺ
    0.05
    æīĢä½ľ
    0.05
     desired
    0.05
     familiar
    0.05
     sob
    0.05
     grasp
    0.05
    转æį¢
    0.05
     (
    0.04
    åıłåĬł
    0.04
    åķ¡
    0.04
    Activations Density 0.003%

    No Known Activations