© 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. 2689
    Prev
    Next
    INDEX
    Explanations

    gradient inducing

    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
     CONCE
    -0.09
    ivate
    -0.09
    upert
    -0.08
    å·®é»ŀ
    -0.08
    çİ¯å²Ľ
    -0.08
     berd
    -0.08
    çĦī
    -0.08
    igente
    -0.08
    `,`
    -0.08
    ecz
    -0.08
    POSITIVE LOGITS
    æŁIJç§į
    0.06
     something
    0.06
    ä¹ĭç±»çļĦ
    0.06
    æ±²
    0.06
    æķĪ
    0.06
     appropriate
    0.06
     alguna
    0.06
    æŁIJæŁIJ
    0.06
     R
    0.06
     relevant
    0.06
    Activations Density 0.072%

    No Known Activations