© 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. 19015
    Prev
    Next
    INDEX
    Explanations

    please provide

    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
    æ¶Ī
    -0.06
    abat
    -0.05
     tup
    -0.05
    uger
    -0.05
    বার
    -0.05
    å¾ĦåIJij
    -0.05
     rat
    -0.05
     ÑģоÑģÑĤавиÑĤ
    -0.05
     il
    -0.05
     unlikely
    -0.05
    POSITIVE LOGITS
    asy
    0.07
     soi
    0.07
    uel
    0.06
    ãs
    0.06
    reau
    0.06
    ercul
    0.06
    deaux
    0.06
    opf
    0.06
    误
    0.06
    orama
    0.05
    Activations Density 0.040%

    No Known Activations