© 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. 47923
    Prev
    Next
    INDEX
    Explanations

    Stage abbreviations (I, II, III)

    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
    urg
    -0.07
    åŁŁçļĦ
    -0.06
    对é½IJ
    -0.06
    对åħ¶ä»ĸ
    -0.06
    éĩĩ
    -0.06
    fram
    -0.06
    inn
    -0.06
    rul
    -0.05
     mov
    -0.05
    æ·»
    -0.05
    POSITIVE LOGITS
    ccount
    0.10
    té
    0.09
    åĬĪ
    0.08
     Twice
    0.08
    óf
    0.08
    ANTE
    0.08
    onsor
    0.08
    óx
    0.08
    åįłåĪ°
    0.08
    å§ij
    0.08
    Activations Density 0.003%

    No Known Activations