© 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. 18021
    Prev
    Next
    INDEX
    Explanations

    study of

    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
     gl
    -0.06
     gent
    -0.06
     fast
    -0.05
    Ñĥж
    -0.05
    ogen
    -0.05
    low
    -0.05
    ·
    -0.05
    знакомиÑĤÑĮÑģÑı
    -0.05
    ÑĢиÑı
    -0.05
     conj
    -0.05
    POSITIVE LOGITS
    плÑİ
    0.07
    aea
    0.06
    ahoo
    0.06
    è¿Ļæĺ¯æĪij们
    0.06
    asio
    0.06
    øg
    0.06
    ียà¸ĩ
    0.06
    ائ
    0.06
    æľĢä½³çŃĶæ¡Ī
    0.06
    éĻIJäºİ
    0.06
    Activations Density 0.002%

    No Known Activations