© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20405
    Prev
    Next
    INDEX
    Explanations

    disclaimer or contains sensitive content

    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
    åį°
    -0.06
    ob
    -0.05
     Hand
    -0.05
    è¹Ń
    -0.05
    åľ°ä½į
    -0.05
    ITU
    -0.05
    رخ
    -0.05
    åīįæıIJ
    -0.05
     except
    -0.05
     aj
    -0.05
    POSITIVE LOGITS
    ément
    0.06
     sav
    0.06
    eya
    0.06
     kyn
    0.06
    ango
    0.05
    tons
    0.05
    é¢Ĺ
    0.05
    skin
    0.05
    è¿Ļ座
    0.05
    楽ãģĹãģ¿ãģ§ãģĻ
    0.05
    Activations Density 0.004%

    No Known Activations