© 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. 21800
    Prev
    Next
    INDEX
    Explanations

    images, videos, photos

    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
    ัà¸ģษà¸ĵะ
    -0.06
    äºij天
    -0.06
    jte
    -0.06
     trụ
    -0.06
    éĵ¶è¡Įä¿¡çĶ¨åį¡
    -0.06
    è½®
    -0.05
    ÏĢÏĦÏħ
    -0.05
     operation
    -0.05
    æ¶İ
    -0.05
     Operation
    -0.05
    POSITIVE LOGITS
    arr
    0.05
    olk
    0.05
    迫害
    0.05
     pace
    0.05
    iger
    0.05
    éĻĮ
    0.05
    }catch
    0.05
    ä¼ģä¸ļèģĮå·¥
    0.05
    resh
    0.05
     rearr
    0.05
    Activations Density 0.010%

    No Known Activations