© 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. 20105
    Prev
    Next
    INDEX
    Explanations

    observable, Var, optional

    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
    oit
    -0.06
    失
    -0.06
    ä½į
    -0.05
    å½¢çļĦ
    -0.05
     Syn
    -0.05
     Temp
    -0.05
    å¸Ń
    -0.05
    igr
    -0.05
    ÃŃ
    -0.05
    yty
    -0.05
    POSITIVE LOGITS
    ebben
    0.07
    ellas
    0.06
    Ùģاض
    0.06
    éĹ®é¢ĺæĿ¥äºĨ
    0.06
    æĹ¥ãģ§
    0.06
    éron
    0.06
     seksi
    0.06
     poorly
    0.05
    ella
    0.05
    enu
    0.05
    Activations Density 0.001%

    No Known Activations