© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 23584
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical context phrases

    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
    ä¹ĭæīĢ以
    -0.09
    —as
    -0.09
    èϽ
    -0.09
    —
    -0.08
     ostensibly
    -0.08
    âĢIJ
    -0.08
     —
    -0.08
    ’
    -0.08
     Likewise
    -0.08
    æīĢè°ĵ
    -0.08
    POSITIVE LOGITS
    )?$
    0.10
    )?
    0.09
    ]?
    0.09
    »?
    0.09
    "?
    0.09
    ))?
    0.09
    }?
    0.08
    )?.
    0.08
    '?
    0.08
    çĮľä½łåĸľæ¬¢
    0.08
    Activations Density 0.025%

    No Known Activations