© 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. 46259
    Prev
    Next
    INDEX
    Explanations

    intrinsic properties and functions

    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
    æī¼
    -0.10
    æ¸ħæ²³
    -0.09
    -assets
    -0.08
    ÐŁÐļ
    -0.07
    HH
    -0.07
    æĨ¬
    -0.07
    åĪĨæķ°
    -0.07
    çļĦé£İéĻ©
    -0.07
    åıªè¦ģèĥ½
    -0.07
    å°Ķé¡¿
    -0.07
    POSITIVE LOGITS
    æľ¬èº«çļĦ
    0.13
     intrinsic
    0.13
    æľ¬èº«
    0.13
    trinsic
    0.11
    æľ¬èº«å°±
    0.11
     inherent
    0.10
    åĽºæľīçļĦ
    0.10
     itself
    0.09
    åĽºæľī
    0.09
    æľ¬èº«å°±æĺ¯
    0.09
    Activations Density 0.076%

    No Known Activations