© 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. 18288
    Prev
    Next
    INDEX
    Explanations

    no follow, no restrictions, no loss

    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
    æıļ
    -0.07
    ypes
    -0.06
    ske
    -0.06
    egar
    -0.06
    enie
    -0.06
    æī¬
    -0.06
    å¼Ħ
    -0.06
    移æ°ijå±Ģ
    -0.05
    egah
    -0.05
     Ske
    -0.05
    POSITIVE LOGITS
    ullo
    0.07
     tal
    0.05
    iro
    0.05
    -sem
    0.05
    ä¸Ģæĸ¹éĿ¢
    0.05
     اÙĦإطÙĦاÙĤ
    0.05
    than
    0.05
     semi
    0.05
    äºİäºĭ
    0.05
     Mont
    0.05
    Activations Density 0.017%

    No Known Activations