© 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. 27903
    Prev
    Next
    INDEX
    Explanations

    Did you try

    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
    eroy
    -0.07
    jera
    -0.07
    deo
    -0.07
     RELATED
    -0.07
     même
    -0.07
     vini
    -0.06
    erlo
    -0.06
     SHALL
    -0.06
    izz
    -0.06
    çĶļèĩ³åľ¨
    -0.06
    POSITIVE LOGITS
     yourself
    0.08
    æīĵç®Ĺ
    0.08
    ä¹IJä¹İ
    0.07
    æľī没æľī
    0.07
    emens
    0.07
    è·ŁæĪij说
    0.07
    ATALOG
    0.07
    æĹ¥ä¹ĭåīį
    0.07
    %%%
    0.07
    è§īå¾Ĺèĩªå·±
    0.07
    Activations Density 0.181%

    No Known Activations