© 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. 21712
    Prev
    Next
    INDEX
    Explanations

    history of

    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
    opportun
    -0.07
    pector
    -0.07
    彬
    -0.06
    gef
    -0.06
    رÙĪÛĮ
    -0.06
    apul
    -0.06
    ä¸Ģ说
    -0.06
    -strokes
    -0.06
     tyl
    -0.06
    å¯¹å·¥ä½ľ
    -0.06
    POSITIVE LOGITS
    èŀįåIJĪäºĨ
    0.06
    èŀįåIJĪ
    0.05
    èŀį
    0.05
     won
    0.05
    èŀįåħ¥
    0.05
    æī¿åıĹçļĦ
    0.05
    ross
    0.05
    mel
    0.05
    div
    0.05
    æ¶īåıĬ
    0.05
    Activations Density 0.058%

    No Known Activations