© 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. 62493
    Prev
    Next
    INDEX
    Explanations

    audio and voice output

    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
    æ®ī
    -0.07
    cope
    -0.07
    ninger
    -0.07
    çĹŀ客éĤ¦
    -0.06
    -scal
    -0.06
    posts
    -0.06
    zon
    -0.06
    ä¸įæĶ¾
    -0.06
    _REDIRECT
    -0.06
    зон
    -0.06
    POSITIVE LOGITS
    åı£å¤´
    0.12
     spoken
    0.12
    åIJ¬è§ī
    0.12
     verbally
    0.11
     oral
    0.11
     orally
    0.11
     verbal
    0.10
    oral
    0.10
     vocal
    0.10
     aloud
    0.10
    Activations Density 0.213%

    No Known Activations