© 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. 21365
    Prev
    Next
    INDEX
    Explanations

    benefit, help, good, become

    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¸įæĺ¯ä¸ºäºĨ
    -0.07
     اÙĦإج
    -0.06
    bens
    -0.06
    duck
    -0.06
    è¾»
    -0.06
    Automatic
    -0.06
    ä¸ĭä¸Ģ级
    -0.06
    Cancelable
    -0.06
    è¯ĹéĽĨ
    -0.06
     Dirig
    -0.06
    POSITIVE LOGITS
    1
    0.05
    agan
    0.05
    ent
    0.05
    è¯ĬæĸŃåıĬ
    0.05
    以æѤ
    0.05
    带ä¸Ĭ
    0.05
    åĽŀæĿ¥åIJİ
    0.04
    ëĮĢìĹIJ
    0.04
    称
    0.04
     Ent
    0.04
    Activations Density 0.008%

    No Known Activations