© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19315
    Prev
    Next
    INDEX
    Explanations

    speech bubble, title, share, album, statement, explains

    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
    ë°ķ
    -0.07
    ingos
    -0.07
    /lists
    -0.06
    ÙĨÚ¯
    -0.06
    å¤įå·¥
    -0.06
     consac
    -0.06
    /respond
    -0.06
     consacré
    -0.06
    ç¾ħæĸ¯
    -0.06
    ä¸Ń以
    -0.06
    POSITIVE LOGITS
     precip
    0.05
     اÙĦشر
    0.05
     Ras
    0.05
    楼主
    0.05
    aget
    0.05
    ä½ĵå¤ĸ
    0.05
    èĪĴéĢĤæĢ§
    0.05
    åħĪåIJİ
    0.04
    ato
    0.04
     sig
    0.04
    Activations Density 0.002%

    No Known Activations