© 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. 48301
    Prev
    Next
    INDEX
    Explanations

    proofs, SELs

    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
    own
    -0.08
    URNS
    -0.07
    çĻ¾å·Ŀ
    -0.07
    ায়
    -0.07
    ensi
    -0.07
    çĻ¾è®¡
    -0.07
    åľ¨çİ°åľº
    -0.07
    Ñĥз
    -0.07
     rasseg
    -0.07
    主è¦ģçļĦ
    -0.07
    POSITIVE LOGITS
     Fonte
    0.07
    çĶ¨å¤Ħ
    0.07
    berger
    0.07
    ×IJ×Ķ
    0.06
    MAND
    0.06
    è²
    0.06
    åĨ¬æĹ¥
    0.06
    andal
    0.06
     Ob
    0.06
    ÏĦÏĮ
    0.06
    Activations Density 0.016%

    No Known Activations