© 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. 26949
    Prev
    Next
    INDEX
    Explanations

    partition coefficient

    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
    ospace
    -0.07
    å®Ľ
    -0.07
    cke
    -0.07
    rng
    -0.06
     argc
    -0.06
    ostream
    -0.06
    éia
    -0.06
     péri
    -0.06
    çĤ¹çģ«
    -0.06
    bord
    -0.06
    POSITIVE LOGITS
    Flip
    0.08
    Importer
    0.08
     Sands
    0.08
    æĤ¬æ®Ĭ
    0.08
    drug
    0.08
     оÑĤноÑĪение
    0.08
    SORT
    0.07
    çľĭ好
    0.07
     droga
    0.07
     Klaus
    0.07
    Activations Density 0.006%

    No Known Activations