© 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. 65267
    Prev
    Next
    INDEX
    Explanations

    explosion, bomb, detonation

    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
    伶
    -0.11
    å·¡è§Ĩåijĺ
    -0.09
    ç³ľ
    -0.08
    çĶĺéľ²
    -0.08
    expédition
    -0.08
    ÑĪенко
    -0.08
    ews
    -0.08
    ergestellt
    -0.08
    olson
    -0.08
    _slope
    -0.08
    POSITIVE LOGITS
     deton
    0.10
     ná»ķ
    0.10
    çĤ¸
    0.09
    çĪĨçĤ¸
    0.08
    åľºéĿ¢
    0.08
    éŀŃçĤ®
    0.08
    /fire
    0.08
    çĤ¸èį¯
    0.08
    arium
    0.08
    å¨ģåĬĽ
    0.08
    Activations Density 0.040%

    No Known Activations