© 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. 25232
    Prev
    Next
    INDEX
    Explanations

    promises, claims, and hype

    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
    diyy
    -0.08
    解
    -0.07
    缸æĢĿ
    -0.07
    å±Ī
    -0.06
     equivalents
    -0.06
     rele
    -0.06
    æŀģäºĨ
    -0.06
    åĪĿäºĮ
    -0.06
    åĬłæ·±
    -0.06
    åĽłçĹħ
    -0.06
    POSITIVE LOGITS
    夸大
    0.14
     unrealistic
    0.13
    声称
    0.12
    宣称
    0.12
     promises
    0.12
     optimistic
    0.12
     promise
    0.12
    ä¹IJè§Ĥ
    0.12
    å®£ä¼ł
    0.11
     claims
    0.11
    Activations Density 0.312%

    No Known Activations