© 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. 39104
    Prev
    Next
    INDEX
    Explanations

    numbered lists

    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
     finally
    -0.09
    finally
    -0.09
     infine
    -0.08
    Finally
    -0.08
    final
    -0.08
    Final
    -0.08
    etc
    -0.08
    æľĢçµĤ
    -0.08
    æľĢç»Ī
    -0.08
     etc
    -0.08
    POSITIVE LOGITS
    åħ¶æ¬¡æĺ¯
    0.08
     âĶľâĶĢâĶĢ
    0.08
    ndo
    0.07
    åħ¶æ¬¡
    0.07
    ense
    0.07
     Redistributions
    0.07
    lose
    0.06
    ?,?,?,?,
    0.06
    avl
    0.06
    opan
    0.06
    Activations Density 0.024%

    No Known Activations