© 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. 50151
    Prev
    Next
    INDEX
    Explanations

    support or corroborate claims/evidence

    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
    aal
    -0.08
    æ³ķå¾ĭéĹ®é¢ĺ
    -0.08
    çŀ»
    -0.08
    oops
    -0.07
    dorf
    -0.07
    кин
    -0.07
    aar
    -0.07
    اØŃØ©
    -0.07
    beau
    -0.07
    ап
    -0.07
    POSITIVE LOGITS
     ÙģÙĥرة
    0.10
     idea
    0.10
    认为
    0.10
    åħ¶çľŁå®ŀæĢ§
    0.10
     bahwa
    0.09
     claims
    0.09
    åħ¶è§ĤçĤ¹
    0.09
     claim
    0.09
    ç»ĵ论
    0.09
     conclusions
    0.09
    Activations Density 0.123%

    No Known Activations