© 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. 38010
    Prev
    Next
    INDEX
    Explanations

    placebo or control group

    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
    ssp
    -0.08
    .cleanup
    -0.08
    èĭįèĿĩ
    -0.07
    antina
    -0.06
    ãĤ¯ãĥ¬
    -0.06
    iri
    -0.06
    ãĤ³ãĥ¼ãĥ«
    -0.06
    è··
    -0.06
    доÑħ
    -0.06
    ecas
    -0.06
    POSITIVE LOGITS
    ostro
    0.08
    åŁºåĩĨ
    0.08
    ëŀĺ
    0.07
    etime
    0.07
    å®ī好
    0.07
     baseline
    0.07
     lá»ĵng
    0.07
    æĹłæķħ
    0.07
    esion
    0.07
    ä¸Ģç½ij
    0.07
    Activations Density 0.207%

    No Known Activations