© 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. 16617
    Prev
    Next
    INDEX
    Explanations

    same with exception

    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
    åIJİæīįèĥ½
    -0.09
    两ä¸į误
    -0.08
    丽ä¸Ŀ
    -0.08
    acia
    -0.08
     ìĹŃìĭľ
    -0.08
    è¿ĶåĽŀé¦ĸ页
    -0.08
    è¡Ķæİ¥
    -0.07
    åĨįæİ¥
    -0.07
    pps
    -0.07
    为éļ¾
    -0.07
    POSITIVE LOGITS
     except
    0.15
     minus
    0.13
    åİ»æİī
    0.11
     Except
    0.11
    minus
    0.10
    except
    0.10
    	except
    0.10
     modified
    0.10
    ä½Ĩ以
    0.10
    éĻ¤åİ»
    0.09
    Activations Density 0.182%

    No Known Activations