© 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. 21690
    Prev
    Next
    INDEX
    Explanations

    reference

    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
    indle
    -0.06
     ×Ķ×IJ×Ĺ
    -0.06
    å¼Ģåıijå·¥ç¨ĭå¸Ī
    -0.06
     quạt
    -0.06
    åħ¢
    -0.06
    ç»ıå®¡æŁ¥
    -0.06
    γγ
    -0.06
    indh
    -0.06
     Ekon
    -0.06
    abant
    -0.06
    POSITIVE LOGITS
    uke
    0.05
     weaken
    0.05
    ural
    0.05
    ental
    0.05
     favor
    0.05
    æį
    0.05
    liner
    0.05
    èģĬèģĬ
    0.05
    uco
    0.05
    ~/
    0.05
    Activations Density 0.002%

    No Known Activations