© 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. 26222
    Prev
    Next
    INDEX
    Explanations

    array with N different integersall zeros of PnAll zeros of fall zeros are realall zeros of P_nall zeros of Pnstring with only '0'sa string consistinga string consistsa cons cella sorted array

    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
    endale
    -0.07
    è¿ĺæľīåħ¶ä»ĸ
    -0.07
    adia
    -0.07
    äºĨåķĬ
    -0.07
    ework
    -0.07
    å»·
    -0.06
    hart
    -0.06
    uld
    -0.06
    èµĦæºIJåħ±äº«
    -0.06
    fs
    -0.06
    POSITIVE LOGITS
    Âł
    0.06
    ĻĤ
    0.06
    è°ĪåĪ°
    0.06
    istringstream
    0.06
    éħ£
    0.06
    authority
    0.06
    Disney
    0.06
     authority
    0.06
    ledes
    0.06
    ç»Ħç»ĩæľºæŀĦ代çłģ
    0.06
    Activations Density 0.007%

    No Known Activations