© 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. 46839
    Prev
    Next
    INDEX
    Explanations

    letter b and number 2

    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
    ĴĪ
    -0.10
    ียว
    -0.08
    á»ģu
    -0.08
    landing
    -0.08
    çĸ²
    -0.07
    Animating
    -0.07
    ä¹Łä¸įæķ¢
    -0.07
    çĶļèĢħ
    -0.07
    å§ij
    -0.07
    åºĻ
    -0.07
    POSITIVE LOGITS
    éĢ
    0.08
    amin
    0.06
    تر
    0.06
    Taken
    0.06
    iph
    0.06
    çļĦäºĭä¸ļ
    0.06
    italia
    0.06
    ;(
    0.06
     pillar
    0.06
    ergen
    0.06
    Activations Density 0.159%

    No Known Activations