© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 61685
    Prev
    Next
    INDEX
    Explanations

    projective space, manifold, Euler

    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
    ftar
    -0.08
    _BLE
    -0.08
    -heart
    -0.08
    ãĥ¼ãĥĹ
    -0.08
    æ±Łè¾¹
    -0.07
    æĻ®åĪ©
    -0.07
    å¦Ĥå±±
    -0.07
     Berlino
    -0.07
    äºİå¿ĥ
    -0.07
     Betr
    -0.07
    POSITIVE LOGITS
    å°Ħ
    0.08
    æĬķ
    0.07
    å®Ŀå®Ŀ们
    0.07
     rays
    0.07
    Ñħо
    0.06
    estate
    0.06
    ernel
    0.06
     shooting
    0.06
     map
    0.06
    æ·»åĬłäºĨ
    0.06
    Activations Density 0.003%

    No Known Activations