© 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. 27663
    Prev
    Next
    INDEX
    Explanations

    climbing or ascending to heights

    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
    åŁĭåľ¨
    -0.08
    éģı
    -0.06
     burst
    -0.06
     ëijĶ
    -0.06
     blo
    -0.06
     swirl
    -0.06
    åŁĭ
    -0.06
    d
    -0.06
    éĺ»å¡ŀ
    -0.06
    屯
    -0.06
    POSITIVE LOGITS
    æĶĢçĪ¬
    0.13
    çĪ¬åĪ°
    0.12
    该平åı°
    0.12
     heights
    0.12
    æĶĢ
    0.12
    -height
    0.12
    çĻ»é«ĺ
    0.12
     precarious
    0.11
    é«ĺå¤Ħ
    0.11
    çĪ¬
    0.11
    Activations Density 0.142%

    No Known Activations