© 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. 22289
    Prev
    Next
    INDEX
    Explanations

    unlikely, rare, uncommon

    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
    è¶Ĭæĺ¯
    -0.07
    çŁ
    -0.06
    æŀĹ
    -0.06
    Mur
    -0.06
    erto
    -0.06
     Æ¡i
    -0.06
     Conditioning
    -0.06
    hind
    -0.06
    Prob
    -0.06
    å°Ī
    -0.06
    POSITIVE LOGITS
    unlikely
    0.11
    å¦Ĥæ¶īåıĬ
    0.09
     rare
    0.08
    гÑĢаÑĦи
    0.08
    ç½ķè§ģ
    0.08
    ç½ķè§ģçļĦ
    0.08
    ibil
    0.08
    ä¼ļæĺ¯
    0.07
    å¦Ĥæŀľæľī
    0.07
     uncommon
    0.07
    Activations Density 0.100%

    No Known Activations