© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    .cv

    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
    @
    -0.07
    çĨĬ
    -0.07
    ger
    -0.06
    agher
    -0.06
     thereafter
    -0.06
    lop
    -0.06
    åIJ§
    -0.06
    å¦Ĥæŀľä½łæĥ³
    -0.06
    çĶ£
    -0.06
    ç¦ģ
    -0.06
    POSITIVE LOGITS
    IVOS
    0.08
    çº¢é¢ľ
    0.08
    åħĪå¾Ĺ
    0.08
    ------+
    0.07
    å°Ķçī¹
    0.07
    thead
    0.07
    ivo
    0.07
     Sebast
    0.07
    .cv
    0.07
    -regexp
    0.07
    Activations Density 0.311%

    No Known Activations