© 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. 26058
    Prev
    Next
    INDEX
    Explanations

    thresholds and cutoff points

    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
    totals
    -0.08
    åħ¸å½ĵ
    -0.08
    riad
    -0.08
     Metropolitana
    -0.08
    çļĦä¸Ģ大
    -0.08
    /dd
    -0.08
    /effects
    -0.07
    å¸Ŀéĥ½
    -0.07
    åĸľè¿İ
    -0.07
    éŨ类
    -0.07
    POSITIVE LOGITS
    æłĩå¿ĹçĿĢ
    0.09
    Reached
    0.08
    éĻĦè¿ij
    0.08
    _finder
    0.08
    éĻĦè¿ijçļĦ
    0.08
     pinpoint
    0.08
     phenomenon
    0.08
     cutoff
    0.08
    çķĮå®ļ
    0.08
     coinc
    0.07
    Activations Density 0.034%

    No Known Activations