© 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. 8332
    Prev
    Next
    INDEX
    Explanations

    becomes vacant, breaks barriers, clock lag

    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
    yw
    -0.08
    æ·±å¤Ħ
    -0.07
     Leip
    -0.07
    æłĩåĩĨè¦ģæ±Ĥ
    -0.07
    éĥ¨åĪĨåĨħ容
    -0.07
    ANCH
    -0.07
    Ïģγο
    -0.07
    สิà¸Ļ
    -0.06
    ampus
    -0.06
    强度é«ĺ
    -0.06
    POSITIVE LOGITS
    .intValue
    0.07
    æ°ij
    0.07
    夷
    0.06
    åĸ¶
    0.06
    ulo
    0.06
    è¿ŀçݯ
    0.06
    obatan
    0.06
    å¬
    0.06
     effected
    0.06
    ulses
    0.06
    Activations Density 0.001%

    No Known Activations