© 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. 21822
    Prev
    Next
    INDEX
    Explanations

    URL fragments or code snippets

    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
    yeti
    -0.06
    جÙħاÙĦÙĬ
    -0.06
    atem
    -0.06
    Ø´ÙĤ
    -0.06
    erche
    -0.06
    -supported
    -0.05
    产åĵģåĪĨç±»
    -0.05
    ailure
    -0.05
    çĶļèĢħ
    -0.05
     garg
    -0.05
    POSITIVE LOGITS
    vap
    0.06
    为人
    0.06
    ID
    0.06
    çľĭèµ·æĿ¥
    0.05
     ade
    0.05
    æ±ĩ
    0.05
    æĿ¥çļĦ
    0.05
    asaran
    0.05
    è´Łè´£äººè¡¨ç¤º
    0.05
    äºij顶
    0.05
    Activations Density 0.003%

    No Known Activations