© 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. 49164
    Prev
    Next
    INDEX
    Explanations

    external

    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
    volle
    -0.09
    iform
    -0.08
    imentos
    -0.08
    ucket
    -0.07
    ifer
    -0.07
    urah
    -0.07
    ecraft
    -0.07
    ÙĦاÙĨ
    -0.07
    ziger
    -0.07
    Ñģев
    -0.07
    POSITIVE LOGITS
    -facing
    0.11
    wards
    0.10
    /internal
    0.10
    çĶ¥
    0.09
    å¤ĸçļĦ
    0.09
     اÙĦخارجÙĬ
    0.09
    /Internal
    0.08
    ternal
    0.08
    å¤ĸéĥ¨
    0.08
    most
    0.08
    Activations Density 0.079%

    No Known Activations