© 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. 19938
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     para
    -0.05
     ap
    -0.05
     adul
    -0.05
    -p
    -0.05
    antro
    -0.05
     fo
    -0.05
     rôle
    -0.05
    åĽłä¸ºæľī
    -0.04
    è¿ĩæľŁ
    -0.04
    ouser
    -0.04
    POSITIVE LOGITS
    atto
    0.07
    alkan
    0.07
    ypi
    0.06
    rades
    0.06
    åİŁåĪĻä¸Ĭ
    0.06
    athom
    0.06
    berge
    0.06
    urah
    0.06
    schnitt
    0.06
     اÙĦتابع
    0.06
    Activations Density 0.034%

    No Known Activations