© 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. 10998
    Prev
    Next
    INDEX
    Explanations

    apollonian networks

    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
    ç³ľ
    -0.07
    å®Įæķ´çļĦ
    -0.07
    å®Įæķ´åľ°
    -0.07
    assel
    -0.07
    (import
    -0.07
     thô
    -0.07
    羣çļ®
    -0.07
    èĤ¥å¤§
    -0.07
     intime
    -0.07
     cất
    -0.07
    POSITIVE LOGITS
     integer
    0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    0.07
    åıijæķ£
    0.07
    pcf
    0.07
    /hooks
    0.07
    åĬĿ
    0.07
    ä¸ī人
    0.07
    æķ´æķ°
    0.07
    æ´½è°Ī
    0.07
    çĭĻ
    0.07
    Activations Density 0.005%

    No Known Activations