© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14888
    Prev
    Next
    INDEX
    Explanations

    lack of

    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
     ulang
    -0.10
    rauch
    -0.10
    иÑģÑĤÑĢа
    -0.10
    azzino
    -0.09
    ิà¹īว
    -0.09
    stants
    -0.09
    icamente
    -0.09
    okable
    -0.09
    ë¦Ń
    -0.09
    ubil
    -0.08
    POSITIVE LOGITS
     hụt
    0.11
    ened
    0.11
    ness
    0.09
    è¶³å¤ŁçļĦ
    0.09
    ening
    0.09
    ed
    0.08
    ingly
    0.08
    lust
    0.08
     sufficient
    0.07
    ht
    0.07
    Activations Density 0.022%

    No Known Activations