© 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. 61035
    Prev
    Next
    INDEX
    Explanations

    equivalence problem

    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
    æĸĹ
    -0.07
     напо
    -0.07
    _unset
    -0.07
    optgroup
    -0.07
    modifiable
    -0.06
    /posts
    -0.06
    orme
    -0.06
    communications
    -0.06
    peng
    -0.06
    atham
    -0.06
    POSITIVE LOGITS
    åħ¨ä½ĵ
    0.08
    evin
    0.08
    羣çIJĨ
    0.08
    lex
    0.08
    çļĦ羣
    0.08
     truth
    0.08
    羣
    0.08
    ees
    0.08
     synt
    0.07
    æľªçĦ¶
    0.07
    Activations Density 0.005%

    No Known Activations