© 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. 42050
    Prev
    Next
    INDEX
    Explanations

    of the step

    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
     judging
    -0.08
    edo
    -0.08
    RGBA
    -0.08
     bols
    -0.08
    кÑĢо
    -0.07
     hẳn
    -0.07
    obao
    -0.07
    çĶľç¾İ
    -0.07
     poleg
    -0.07
     *)((
    -0.07
    POSITIVE LOGITS
     step
    0.07
    çļĨæľī
    0.07
    arrant
    0.07
    骤
    0.07
    ely
    0.07
    è·¯ä¸ĬçļĦ
    0.06
    ãģ®ãģĶ
    0.06
    -step
    0.06
    uesa
    0.06
    ript
    0.06
    Activations Density 0.005%

    No Known Activations