© 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. 18425
    Prev
    Next
    INDEX
    Explanations

    function definition

    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
    adah
    -0.06
    为满足
    -0.06
    am
    -0.06
    еÑħ
    -0.06
    为äºĨ满足
    -0.05
    éĺ¿å¾·
    -0.05
    classed
    -0.05
     vor
    -0.05
    ÑģÑĤеÑģÑĤвенно
    -0.05
    நà¯įத
    -0.05
    POSITIVE LOGITS
    polis
    0.06
    aspers
    0.06
    fare
    0.06
    ünden
    0.05
    egna
    0.05
    ä½Ľç¥ĸ
    0.05
    ovich
    0.05
    å¸ĮæľĽå¯¹å¤§å®¶
    0.05
    bove
    0.05
    æŃ¢
    0.05
    Activations Density 0.002%

    No Known Activations