© 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. 17462
    Prev
    Next
    INDEX
    Explanations

    other or another

    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
    ex
    -0.06
    å½¢å¼ı
    -0.05
    extr
    -0.05
    w
    -0.05
     Ex
    -0.05
    ...
    -0.05
    Q
    -0.05
    -
    -0.05
    ç³»ç»Ł
    -0.05
    antar
    -0.05
    POSITIVE LOGITS
    滩
    0.07
    çģĺ
    0.07
    æĶ¹éĢłé¡¹çĽ®
    0.07
    åħ¨éĿ¢å»ºæĪIJ
    0.07
    å·´åĭĴ
    0.06
    fällen
    0.06
    emoc
    0.06
     tenden
    0.06
    ific
    0.06
     verkligen
    0.06
    Activations Density 0.021%

    No Known Activations