© 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. 21876
    Prev
    Next
    INDEX
    Explanations

    primary election choices

    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
    enen
    -0.06
    æĺ±
    -0.05
    ä»ģ
    -0.05
    éĿĸ
    -0.05
     flexGrow
    -0.05
    ems
    -0.05
    æĺı
    -0.05
    å¼ģ
    -0.05
    å¾ĹäºĨ
    -0.05
    æĽ³
    -0.05
    POSITIVE LOGITS
    举è¡Ĺ
    0.08
    еÑĩи
    0.06
     khai
    0.06
    yerek
    0.06
    çĪ±èĩªå·±
    0.06
    æĹłçºº
    0.06
    æĹłåīį
    0.06
    ÎŃÏģγ
    0.06
     prochains
    0.06
    æĻºèģĶ
    0.06
    Activations Density 0.002%

    No Known Activations