© 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. 12147
    Prev
    Next
    INDEX
    Explanations

    anti-bride, typical, office clothes, hot colors, pretension

    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
    大æĦı
    -0.06
    _CI
    -0.06
    å¯
    -0.06
    èĻ½çĦ¶ä¸įæĺ¯
    -0.06
    åĴĮå¹³
    -0.06
     Del
    -0.06
    uddle
    -0.06
    uel
    -0.05
    F
    -0.05
     Clo
    -0.05
    POSITIVE LOGITS
    æĿ¡æĿ¡
    0.10
     clich
    0.09
    éĥ¨å°±
    0.09
    åĪ»æĦı
    0.09
    eszt
    0.09
    åĬŁåĪ©
    0.08
    è¿ĩå¤ļçļĦ
    0.08
    blätter
    0.08
    addy
    0.08
    anax
    0.08
    Activations Density 0.245%

    No Known Activations