© 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. 43147
    Prev
    Next
    INDEX
    Explanations

    output

    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
    大å¸Ŀ
    -0.07
    çĶ¨åĪ°
    -0.06
    ozo
    -0.06
    åĪĿæľŁ
    -0.06
    enga
    -0.06
    æ¶īåıĬåĪ°
    -0.06
    jan
    -0.06
    beck
    -0.06
    åį´æĹłæ³ķ
    -0.06
    åį´ä¸įèĥ½
    -0.06
    POSITIVE LOGITS
     output
    0.11
    è¾ĵåĩº
    0.11
    output
    0.11
    Output
    0.10
     Output
    0.10
    çļĦè¾ĵåĩº
    0.10
    è¾ĵåĩºçļĦ
    0.10
     outputs
    0.09
    .Output
    0.09
    =output
    0.09
    Activations Density 0.007%

    No Known Activations