© 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. 21143
    Prev
    Next
    INDEX
    Explanations

    no restrictions

    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
    keit
    -0.06
    ä¹ŁæĽ´
    -0.05
     prega
    -0.05
    ìĪĺë¡Ŀ
    -0.05
    oid
    -0.05
    rego
    -0.05
    mal
    -0.05
    è·¡
    -0.05
     âĢ¢
    -0.05
    å®ľ
    -0.05
    POSITIVE LOGITS
    åı¯è¨Ģ
    0.06
    nat
    0.06
    çĶ¨è¿ĩ
    0.06
    abri
    0.06
    ebas
    0.06
    åIJĦå¸Ĥ
    0.06
    ç»ĵäºĨ
    0.05
    年以ä¸ĭ
    0.05
    æ¼ł
    0.05
    è´¸
    0.05
    Activations Density 0.415%

    No Known Activations