© 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. 49814
    Prev
    Next
    INDEX
    Explanations

    project 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
    ickle
    -0.08
    uzzer
    -0.08
    halat
    -0.08
    ifat
    -0.08
    elan
    -0.08
    unsch
    -0.08
    çĽ¸å®¹
    -0.08
    uzz
    -0.08
    perator
    -0.08
    addTo
    -0.08
    POSITIVE LOGITS
     step
    0.09
     Step
    0.07
     steps
    0.07
    Step
    0.07
    step
    0.07
    -step
    0.07
     conduct
    0.07
     krok
    0.06
     STEP
    0.06
    æŃ¥éª¤
    0.06
    Activations Density 0.006%

    No Known Activations