© 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. 24994
    Prev
    Next
    INDEX
    Explanations

    sorption, films, nanoparticles, isolate, fermented

    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
    çĮ
    -0.08
    çŃĸ
    -0.07
    çľ·
    -0.07
    åºĶå½ĵ
    -0.07
    Impossible
    -0.07
    å¹²éĥ¨éĺŁä¼į
    -0.07
    Åį
    -0.07
     champagne
    -0.07
     famously
    -0.07
    èĬľ
    -0.07
    POSITIVE LOGITS
    ä¸İä¼łç»Ł
    0.08
    pret
    0.08
    æľ¬çłĶ究
    0.07
    èĩªåĪ¶
    0.07
    prepared
    0.07
    parameters
    0.07
    æݢ讨äºĨ
    0.07
    ä¹ĭå¤ľ
    0.07
    Parameters
    0.07
     promising
    0.07
    Activations Density 2.171%

    No Known Activations