© 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. 49297
    Prev
    Next
    INDEX
    Explanations

    southwest soldier

    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
    èĢĮå¾ĹåIJį
    -0.08
    以ä¸ĭç®Ģ称
    -0.07
    èİĺ
    -0.06
    天éķ¿
    -0.06
    MBOL
    -0.06
    ç»İ
    -0.06
    styleType
    -0.06
    téri
    -0.06
    ardless
    -0.06
    åħ¶çľŁå®ŀæĢ§
    -0.06
    POSITIVE LOGITS
    åIJĮçIJĨ
    0.10
    åĪĻ以
    0.08
     hingegen
    0.08
    åĪĻéľĢè¦ģ
    0.08
    åĪĻå°Ĩ
    0.08
     же
    0.08
    亦çĦ¶
    0.08
    ä¹Łæĺ¯ä¸Ģæł·
    0.08
    åĪĻçĶ±
    0.08
    åĪĻæĺ¯
    0.08
    Activations Density 0.006%

    No Known Activations