© 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. 26109
    Prev
    Next
    INDEX
    Explanations

    focusing on description

    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
    ä¸Ģå¹´åĽĽåŃ£
    -0.08
     konst
    -0.07
    leit
    -0.07
    å§IJ
    -0.07
    éĢļè¿ĩåIJĦç§į
    -0.07
    è®°å½ķäºĨ
    -0.07
    åijĹ
    -0.07
    ?q
    -0.06
     recorded
    -0.06
    record
    -0.06
    POSITIVE LOGITS
    æĥ³çľĭ
    0.09
    ross
    0.08
     focus
    0.08
    Focus
    0.08
    ä¸įå¿ħè¦ģ
    0.08
     focusing
    0.08
    éĢĤéĩıçļĦ
    0.07
     Focus
    0.07
    cala
    0.07
    çĤ¹åĪ°
    0.07
    Activations Density 0.025%

    No Known Activations