© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 52036
    Prev
    Next
    INDEX
    Explanations

    overlap, overflow, outgrowth

    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
    Negative Logits
    çĤ³
    -0.07
    ttes
    -0.06
    åĨ·åĨ·
    -0.06
     Ber
    -0.06
    å¤Ħ
    -0.06
     aged
    -0.06
    CanBe
    -0.06
     resign
    -0.06
    AGES
    -0.06
    decl
    -0.06
    POSITIVE LOGITS
    è¶Ĭè¿ĩ
    0.13
     overlapping
    0.13
     overlaps
    0.13
     overlap
    0.13
    Overlap
    0.13
    è¦ĨçĽĸäºĨ
    0.12
    overlap
    0.12
    _overlap
    0.12
    触åıĬ
    0.11
    è·¨è¿ĩ
    0.11
    Activations Density 0.180%

    No Known Activations