© 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. 16191
    Prev
    Next
    INDEX
    Explanations

    procedure, converting, necessity

    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
    ä¸Ģç½ij
    -0.08
    è¶ħæŶ
    -0.07
    rama
    -0.07
    odian
    -0.07
    建æĪIJ
    -0.07
    à¸Ħิว
    -0.06
    ehlen
    -0.06
    è¿ĻäºĽä¿¡æģ¯
    -0.06
    åħ¨éĿ¢å»ºæĪIJ
    -0.06
     timeouts
    -0.06
    POSITIVE LOGITS
    éĩįæĸ°
    0.09
    çļĦæĶ¹åıĺ
    0.09
    åİŁæľī
    0.09
    æĶ¹åıĺçļĦ
    0.09
     alteration
    0.09
    æĶ¹åıĺäºĨ
    0.09
     alterations
    0.09
     resh
    0.09
    æĶ¹åıĺ
    0.08
     drastic
    0.08
    Activations Density 0.344%

    No Known Activations