© 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. 20051
    Prev
    Next
    INDEX
    Explanations

    Additional settings and features

    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
    å½ĵä¹ĭæĹłæĦ§
    -0.08
    .Types
    -0.08
    deel
    -0.07
     literally
    -0.07
     Heights
    -0.07
    heen
    -0.06
    lighet
    -0.06
    /types
    -0.06
     ÑģкÑĥ
    -0.06
    ISTI
    -0.06
    POSITIVE LOGITS
    诸å¦Ĥ
    0.12
    è¿ĺåĮħæĭ¬
    0.12
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.11
    çļĦåħ¶ä»ĸ
    0.10
     miscellaneous
    0.10
    à¸Ńืà¹Īà¸Ļà¹Ĩ
    0.10
    additional
    0.10
    çŃīåħ¶ä»ĸ
    0.10
    Additional
    0.10
    åħ¶ä»ĸ
    0.10
    Activations Density 0.130%

    No Known Activations