© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22349
    Prev
    Next
    INDEX
    Explanations

    what is

    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
     **:**
    -0.06
    Äıte
    -0.06
    ahkan
    -0.06
    acements
    -0.06
    eldon
    -0.06
    Ðĵи
    -0.06
    éºĵ
    -0.06
    akhir
    -0.05
    urkan
    -0.05
    ãĤº
    -0.05
    POSITIVE LOGITS
    etto
    0.06
     ÑĥÑģл
    0.06
    uta
    0.05
    enor
    0.05
    pok
    0.05
    æĦı義
    0.05
    è¿°
    0.05
    %B
    0.05
    ook
    0.05
    ä»ģçĪ±
    0.05
    Activations Density 0.016%

    No Known Activations