© 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. 4882
    Prev
    Next
    INDEX
    Explanations

    from a/the

    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
    AndGet
    -0.06
    даÑĢ
    -0.06
    æĶ¶å½ķ
    -0.05
    iser
    -0.05
    uj
    -0.05
    å¾ĹåĪ°
    -0.05
     fall
    -0.05
     enc
    -0.05
    swer
    -0.05
     ability
    -0.05
    POSITIVE LOGITS
    resse
    0.08
    idang
    0.08
    kring
    0.08
    ovas
    0.08
    chenk
    0.08
    istere
    0.08
    ÅĦcz
    0.08
    çIJ²
    0.08
    rira
    0.08
    rador
    0.08
    Activations Density 0.026%

    No Known Activations