© 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. 50439
    Prev
    Next
    INDEX
    Explanations

    mathematical function derivatives

    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
    iam
    -0.06
    mira
    -0.06
    igor
    -0.06
    åĸĩ
    -0.06
    _equals
    -0.06
    b
    -0.06
    rio
    -0.06
    a
    -0.06
    ÑĥÑĩ
    -0.06
    alin
    -0.06
    POSITIVE LOGITS
    avais
    0.08
    GRE
    0.08
    gre
    0.08
    à¹Īà¸Ńà¸ĩ
    0.08
    ixe
    0.08
    folge
    0.07
    被æµıè§Ī
    0.07
    à¹īà¸Ńà¸Ļ
    0.07
    hints
    0.07
    .ds
    0.07
    Activations Density 0.023%

    No Known Activations