© 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. 20006
    Prev
    Next
    INDEX
    Explanations

    ms or state prefixes

    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
    wards
    -0.07
    ory
    -0.06
    retta
    -0.06
     paru
    -0.06
    ORY
    -0.06
    γη
    -0.06
    WARDS
    -0.06
    bym
    -0.05
     slightest
    -0.05
    ahui
    -0.05
    POSITIVE LOGITS
    æĪij们æīĢ
    0.05
    >:</
    0.05
    ä¸Ģç§į
    0.05
    åįĥç§ĭ
    0.05
    HAD
    0.04
    æ¶ī
    0.04
    ÙħÙĪÙĨ
    0.04
     momentarily
    0.04
     literally
    0.04
    ãģĵãģ¨ãģ§ãģĹãĤĩãģĨ
    0.04
    Activations Density 0.006%

    No Known Activations