© 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. 20875
    Prev
    Next
    INDEX
    Explanations

    that the whole

    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
    ä½ķå¤Ħ
    -0.06
    åı¯èĥ½å°±
    -0.06
    egin
    -0.05
    è¿IJåĬ¨åĴĮ
    -0.05
    AYER
    -0.05
    ipo
    -0.05
    egan
    -0.05
     learners
    -0.05
    ä¹ĭå¤ļ
    -0.05
    amma
    -0.05
    POSITIVE LOGITS
    знаÑĩ
    0.06
    otec
    0.06
     necessarily
    0.06
     satisfa
    0.05
    ogeneous
    0.05
    wart
    0.05
    ç±į
    0.05
    æŃ£å½ĵ
    0.05
    zin
    0.05
    agenta
    0.05
    Activations Density 0.010%

    No Known Activations