© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 10363
    Prev
    Next
    INDEX
    Explanations

    rules, methods, guidelines

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æīĵéĢłæĪIJ
    -0.09
    æIJľç´¢çĽ¸åħ³èµĦæĸĻ
    -0.09
    åķıãģĦ
    -0.08
     envis
    -0.08
    Extern
    -0.08
    jukan
    -0.08
    otime
    -0.08
    andong
    -0.08
    ynet
    -0.08
    该产åĵģ
    -0.07
    POSITIVE LOGITS
    è§ĦåĪĻ
    0.12
    åŁºæľ¬åİŁåĪĻ
    0.11
    çļĦè§ĦåĪĻ
    0.11
     rules
    0.11
    æľīçļĦæŶåĢĻ
    0.11
     rule
    0.10
    è§ĦåĪĻåĴĮ
    0.10
     guidelines
    0.10
    åİŁåĪĻ
    0.10
    åı£è¯Ģ
    0.10
    Activations Density 0.086%

    No Known Activations