© 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. 17272
    Prev
    Next
    INDEX
    Explanations

    creative writing and publications

    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
     sichtbar
    -0.06
    æ´ªæµģ
    -0.06
    jte
    -0.06
    å¸Ĥåºľ
    -0.06
    å¦Ĥæ½®
    -0.06
     hoor
    -0.06
    azza
    -0.06
    é§ħãģĭãĤīå¾ĴæŃ©
    -0.06
    åĩĢæµģåĩº
    -0.06
    浪èĬ±
    -0.06
    POSITIVE LOGITS
    otto
    0.06
    θα
    0.05
    voll
    0.05
    à¹Ģà¸Ńà¸ĩ
    0.05
    apa
    0.05
     lâu
    0.05
    olo
    0.05
    zun
    0.05
    عÙĩ
    0.05
    常è§Ħ
    0.05
    Activations Density 0.004%

    No Known Activations