© 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. 17130
    Prev
    Next
    INDEX
    Explanations

    listing names and places

    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
    ente
    -0.05
    N
    -0.05
     grad
    -0.05
     gr
    -0.05
    illar
    -0.04
     sus
    -0.04
     earth
    -0.04
    }):
    -0.04
    /Sub
    -0.04
    om
    -0.04
    POSITIVE LOGITS
    ä¸į解
    0.07
     seputar
    0.07
    ÑģÑĤеÑģÑĤвенно
    0.07
    uló
    0.06
    çļĦè¿ĺæĺ¯
    0.06
    lega
    0.06
    èĺ
    0.06
    ÄĻp
    0.06
    egl
    0.06
    åŁºæľ¬æ¦Ĥ念
    0.06
    Activations Density 0.006%

    No Known Activations