© 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. 64790
    Prev
    Next
    INDEX
    Explanations

    Sr. or Jr

    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
    ahi
    -0.06
    鼰
    -0.06
    çĶļ麼
    -0.05
    åħ¬åħ±é¢Ħç®Ĺ
    -0.05
    éĹĨ
    -0.05
    aru
    -0.05
    ��
    -0.05
    ufer
    -0.05
    <|object_ref_start|>
    -0.05
    Ñĥк
    -0.05
    POSITIVE LOGITS
    请èģĶç³»æĪij们
    0.07
    baugh
    0.07
    iores
    0.07
    ecas
    0.06
    zwi
    0.06
    <|endoftext|>
    0.06
    $request
    0.06
    çĺ
    0.06
    iems
    0.06
    qus
    0.06
    Activations Density 0.002%

    No Known Activations