© 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. 33317
    Prev
    Next
    INDEX
    Explanations

    hyphenated -phobia words

    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
    æī©å±ķèµĦæĸĻ
    -0.08
    åıĪéģĵ
    -0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.08
    æľįåĬ¡çŃī
    -0.08
    çĽĺé¾Ļ
    -0.08
    gat
    -0.07
    å¿ĥçĶ°
    -0.07
    éĢļè¿ĩè¿ĻäºĽ
    -0.07
    _locked
    -0.07
    åıĪæĺ¯ä¸Ģ
    -0.07
    POSITIVE LOGITS
    ifle
    0.06
    ä¹ĭæīĢ以
    0.06
     ê
    0.06
    æ¦Ĥ
    0.06
    ä¸ŀ
    0.06
     Burl
    0.05
     sogenannte
    0.05
    inkle
    0.05
     bitcoin
    0.05
    olutely
    0.05
    Activations Density 0.027%

    No Known Activations