© 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. 20914
    Prev
    Next
    INDEX
    Explanations

    someone

    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
    utti
    -0.06
     grie
    -0.05
     incor
    -0.05
    าà¸Ī
    -0.05
    çī¹æ´¾
    -0.05
    åī¥
    -0.05
    ç¾İæľ¯åѦéĻ¢
    -0.05
    άÏĤ
    -0.05
    εια
    -0.05
     forth
    -0.05
    POSITIVE LOGITS
    è°ĥ
    0.06
    åŀĴ
    0.05
    ä»ħ次äºİ
    0.05
     net
    0.05
    ä¸įä¸ĭ
    0.05
    ä¸įåĩº
    0.05
    inesis
    0.05
    好å¤ĦçļĦ
    0.05
    ä¸Ģå¤Ħ
    0.05
    å¼ł
    0.05
    Activations Density 0.002%

    No Known Activations