© 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. 24283
    Prev
    Next
    INDEX
    Explanations

    ready, use, power, functions, environment

    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
    æīįèĥ½ä½¿
    -0.09
    æīįèĥ½å¾ĹåĪ°
    -0.08
    æīįèĥ½è®©
    -0.08
    Ỽt
    -0.08
    ebro
    -0.08
    åħ¶æ¬¡æĺ¯
    -0.08
     Secondly
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.08
    è¿Ļ两款
    -0.08
    æĭħ
    -0.07
    POSITIVE LOGITS
     finally
    0.09
    finally
    0.09
    èĩ³æѤ
    0.08
     voilÃł
    0.08
    æł¹æį®éľĢè¦ģ
    0.08
     hopefully
    0.08
     infine
    0.08
    以ä¸Ĭå°±æĺ¯
    0.08
    å¦ĤéľĢ
    0.08
     finalmente
    0.07
    Activations Density 0.113%

    No Known Activations