© 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. 42630
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    æĺŁæłĩ
    -0.07
    åıijæī¬
    -0.07
    ä¸įæŃ£
    -0.07
    "].(
    -0.06
    ÙĨÛĮÙĨ
    -0.06
    éĩijçīĽ
    -0.06
    itled
    -0.06
    çķ¥æľī
    -0.06
    itized
    -0.06
    çķ¥
    -0.06
    POSITIVE LOGITS
    è¯ģæį®è¯ģæĺİ
    0.08
    inerary
    0.07
    æ³ķå¾ĭ顾éĹ®
    0.07
    YNC
    0.07
    .Encoding
    0.07
     dern
    0.07
    çŁ¥è¯Ĩä¸İ
    0.07
    Lic
    0.07
    dump
    0.07
    _Enc
    0.07
    Activations Density 0.000%

    No Known Activations