© 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. 33013
    Prev
    Next
    INDEX
    Explanations

    scientific notation or date/system prefixes

    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
    unn
    -0.09
    Ĥ¹
    -0.08
    ложе
    -0.08
    ZA
    -0.08
    注éĶĢå¤ĩæ¡Ī
    -0.08
    éĶ¦æ¶Ľ
    -0.08
    <typeof
    -0.08
    æľĪä¸ĬæŬ
    -0.08
    ç½ĹéĤ£
    -0.08
    URRE
    -0.08
    POSITIVE LOGITS
    -
    0.08
    âĢ
    0.07
     -
    0.06
    Âł
    0.06
    _rt
    0.06
    çĤŃ
    0.06
    0.06
    —
    0.05
     charter
    0.05
    ons
    0.05
    Activations Density 0.001%

    No Known Activations