© 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. 17550
    Prev
    Next
    INDEX
    Explanations

    out

    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
    ä¸į平衡
    -0.06
     never
    -0.05
    ¦
    -0.05
    件äºĭ
    -0.05
    æĿłæĿĨ
    -0.05
    åıijè§ī
    -0.05
     exist
    -0.05
    ider
    -0.05
     Pers
    -0.05
     sensit
    -0.05
    POSITIVE LOGITS
    模ç³Ĭ
    0.08
    çľĭä¸įæ¸ħ
    0.07
    ä¸įæ¸ħ
    0.07
     vision
    0.07
    vision
    0.07
    blur
    0.07
    è§ĨåĬĽ
    0.07
    Vision
    0.07
     comod
    0.07
    Blur
    0.07
    Activations Density 0.033%

    No Known Activations