© 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. 17163
    Prev
    Next
    INDEX
    Explanations

    group of players

    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
    ä¹ĭä¸Ģæĺ¯
    -0.06
    ä¹ĭä¸ĢçļĦ
    -0.06
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.06
    omic
    -0.06
    lach
    -0.05
    è¶ĭ
    -0.05
    aver
    -0.05
    quate
    -0.05
    indik
    -0.05
    _example
    -0.05
    POSITIVE LOGITS
    类似
    0.07
    类似çļĦ
    0.06
     simila
    0.06
    é¢Ĥ
    0.06
    Score
    0.06
     progressively
    0.06
     Sieg
    0.05
     similarly
    0.05
     similar
    0.05
    enna
    0.05
    Activations Density 0.177%

    No Known Activations