© 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. 17510
    Prev
    Next
    INDEX
    Explanations

    other [adjective]

    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
    atot
    -0.06
    اÙĪر
    -0.06
    аÑģÑĤ
    -0.05
    irin
    -0.05
    ischer
    -0.05
     asymmetric
    -0.05
    endir
    -0.05
    eur
    -0.05
     اÙĦجز
    -0.05
    eri
    -0.05
    POSITIVE LOGITS
    缸åħ³éĺħ读
    0.06
    omma
    0.06
     cÆ°Æ¡ng
    0.05
    ä»ĵ
    0.05
    koli
    0.05
    oked
    0.05
    æļ´éľ²
    0.05
    åįļè§Ī
    0.05
     Coy
    0.05
    åĢī
    0.05
    Activations Density 0.016%

    No Known Activations