© 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. 18006
    Prev
    Next
    INDEX
    Explanations

    desire or openness to action

    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
    æĦıåIJij
    -0.06
    %X
    -0.05
    ä¸įéĢĢ
    -0.05
    ê°ģ
    -0.05
    å¸ľ
    -0.05
    uien
    -0.05
    èĢ¸
    -0.05
    åĿļ
    -0.05
    éĹĬ
    -0.05
    ibox
    -0.05
    POSITIVE LOGITS
     toler
    0.07
     preferred
    0.06
    agg
    0.06
    éľĢè¦ģçļĦ
    0.06
    追æ±Ĥ
    0.06
    æľĢéľĢè¦ģ
    0.06
     prefer
    0.06
     bevorzug
    0.06
    å¹³
    0.06
    oler
    0.05
    Activations Density 0.122%

    No Known Activations