© 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. 14943
    Prev
    Next
    INDEX
    Explanations

    outcomes or states

    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
    å½ĵçĦ¶è¦ģ
    -0.08
    èĥ½å¤ŁæľīæķĪ
    -0.07
    .sw
    -0.07
    æ¯ĵ
    -0.07
    mati
    -0.06
     s
    -0.06
     FSM
    -0.06
    æīķ
    -0.06
     qualifies
    -0.06
     DPD
    -0.06
    POSITIVE LOGITS
     ebenfalls
    0.09
    åħ¶å®ĥçļĦ
    0.08
    oglio
    0.08
    ãģĵãģ¡ãĤīãĤĤ
    0.08
     igualmente
    0.08
    elon
    0.08
     juist
    0.08
     sólo
    0.07
     altogether
    0.07
    chè
    0.07
    Activations Density 0.730%

    No Known Activations