© 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. 16914
    Prev
    Next
    INDEX
    Explanations

    our commitment to you

    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
    tro
    -0.07
     tro
    -0.06
    å²±
    -0.06
    cim
    -0.06
     Tro
    -0.06
     considéra
    -0.06
    ìĪľ
    -0.06
    è¿Ļ两ä½į
    -0.06
    имÑĥÑīеÑģÑĤв
    -0.06
    these
    -0.06
    POSITIVE LOGITS
    æĹłéĿŀ
    0.05
    ç»ıçIJĨ
    0.05
     journey
    0.05
     Âł
    0.05
    pecially
    0.05
    è¿ĻéĩĮæľī
    0.05
    å°¤åħ¶
    0.05
    è´£
    0.05
    bra
    0.05
    å°¤åħ¶æĺ¯åľ¨
    0.05
    Activations Density 0.053%

    No Known Activations