© 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. 57398
    Prev
    Next
    INDEX
    Explanations

    anion / anions

    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
    a
    -0.10
    ally
    -0.08
     volna
    -0.07
    ×Ķ
    -0.07
    ãģ¾ãģĹãģ¦
    -0.06
    ाà¤ĩ
    -0.06
    ãĥ³
    -0.06
    lech
    -0.06
    ा
    -0.06
    ëĭ¤
    -0.06
    POSITIVE LOGITS
    lässlich
    0.13
    Ø©
    0.13
    ness
    0.12
    xious
    0.11
    efined
    0.11
    wser
    0.10
    rew
    0.10
    áŁĭ
    0.10
    ation
    0.10
    ecess
    0.10
    Activations Density 0.041%

    No Known Activations