© 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. 57767
    Prev
    Next
    INDEX
    Explanations

    spatial location and distance

    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
    óz
    -0.06
    æg
    -0.06
     progres
    -0.06
    çķĻç»Ļ
    -0.06
     Manit
    -0.06
    اØŃت
    -0.06
    éĶ¯é½¿
    -0.06
    è°ĥæķ´åĴĮ
    -0.06
    ä¸İæĻ®éĢļ
    -0.06
    _slope
    -0.06
    POSITIVE LOGITS
     Abstand
    0.08
     distances
    0.08
    è¿ľç¦»
    0.08
     distance
    0.07
    å±Ģ
    0.07
    è·ĿéĽ¢
    0.07
     perpendicular
    0.07
     befind
    0.07
    çĺ¾
    0.07
    亥
    0.07
    Activations Density 0.005%

    No Known Activations