© 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. 18357
    Prev
    Next
    INDEX
    Explanations

    total sum equal zero

    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
     enough
    -0.05
    indre
    -0.05
    ÑİÑĢ
    -0.05
     Enough
    -0.05
    nil
    -0.05
    çħİ
    -0.05
    åºĹ
    -0.05
    ÅĽni
    -0.05
    çĩŁ
    -0.05
    æ±ģ
    -0.05
    POSITIVE LOGITS
    adies
    0.06
    åĽŃè·¯
    0.06
    éĩı为
    0.05
    vary
    0.05
    quilibr
    0.05
    管çIJĨç±»
    0.05
    ãĤ¢ãĤ¯ãĤ»
    0.05
    !(:
    0.05
    æŁ»
    0.05
    第ä¸Ģ线
    0.05
    Activations Density 0.002%

    No Known Activations