© 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. 48004
    Prev
    Next
    INDEX
    Explanations

    rejection or rejected

    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
    åŃ¦å®¶
    -0.08
    versa
    -0.08
    cle
    -0.08
    รายà¸ģาร
    -0.08
    versorgung
    -0.08
    klet
    -0.08
    riages
    -0.08
    enne
    -0.08
    ajukan
    -0.08
    vento
    -0.07
    POSITIVE LOGITS
    ably
    0.11
    ive
    0.10
    OrCreate
    0.09
    æİīçļĦ
    0.09
    ا
    0.08
    æİī
    0.08
    ments
    0.08
    اÙĭ
    0.08
    ات
    0.07
    erait
    0.07
    Activations Density 0.010%

    No Known Activations