© 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. 40376
    Prev
    Next
    INDEX
    Explanations

    depth needed

    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
     limits
    -0.09
     Limits
    -0.09
    Limits
    -0.08
    åıªèĥ½çĶ¨
    -0.08
     limiting
    -0.08
     maxim
    -0.08
    éĻIJ
    -0.08
    ä¸įå¾Ĺè¶ħè¿ĩ
    -0.08
     maximize
    -0.08
     limited
    -0.08
    POSITIVE LOGITS
    è¶³å¤ŁçļĦ
    0.20
     sufficient
    0.19
    è¶³å¤Ł
    0.19
     enough
    0.18
    èĩ³å°ijè¦ģ
    0.16
    足以
    0.16
     sufficiently
    0.15
    è¶³å¤ł
    0.15
     minimum
    0.15
    å¤Ł
    0.15
    Activations Density 0.121%

    No Known Activations