© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2924
    Prev
    Next
    INDEX
    Explanations

    limit zero

    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
     Lemb
    -0.07
    ÏĢοÏħ
    -0.07
    ëįľ
    -0.07
    è½®
    -0.07
    ônio
    -0.07
     Setia
    -0.07
    _POLL
    -0.06
    quit
    -0.06
    Ł
    -0.06
    added
    -0.06
    POSITIVE LOGITS
    ä¹ĭéĻħ
    0.08
    ä¹ĭéļĽ
    0.08
    hofer
    0.08
    ish
    0.07
    å®£ä¼łè´¯å½»
    0.07
    åħ®
    0.07
    bones
    0.07
    oeff
    0.06
    æľīå¦Ĥ
    0.06
    ramer
    0.06
    Activations Density 0.002%

    No Known Activations