© 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. 23871
    Prev
    Next
    INDEX
    Explanations

    exceeded or acceptable

    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
    æ±ĩéĽĨ
    -0.09
    å°½éĩıåĩıå°ij
    -0.08
    åĮºåĪ«äºİ
    -0.08
    Distinct
    -0.08
    ysz
    -0.07
     RequestContext
    -0.07
    æ±ĩéĽĨäºĨ
    -0.07
    enho
    -0.07
    æŀ«
    -0.07
    _CSR
    -0.07
    POSITIVE LOGITS
    è¾¾æłĩ
    0.10
     borderline
    0.10
     exceeded
    0.10
    è¶ħæłĩ
    0.09
     exceeds
    0.09
     undercut
    0.08
     exceed
    0.08
     shortfall
    0.08
    ç»°
    0.08
     пÑĢевÑĭ
    0.08
    Activations Density 0.016%

    No Known Activations