© 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. 27056
    Prev
    Next
    INDEX
    Explanations

    more than

    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
    jd
    -0.07
    èĩªæĭĶ
    -0.07
    éĴ¦
    -0.07
    akers
    -0.06
    istr
    -0.06
    umas
    -0.06
    ici
    -0.06
    广
    -0.06
    è¡ĮåĬ¨ä¸Ń
    -0.06
    иÑĤаÑĢ
    -0.06
    POSITIVE LOGITS
    árt
    0.08
    oyal
    0.07
    ála
    0.07
    å¦į
    0.07
    ouro
    0.07
     filmy
    0.07
    wurf
    0.07
    ORM
    0.07
    tuj
    0.07
    åħ¢åħ¢ä¸ļä¸ļ
    0.07
    Activations Density 0.250%

    No Known Activations