© 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. 13323
    Prev
    Next
    INDEX
    Explanations

    metallic or elemental form

    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
    æµģ水线
    -0.08
    Merge
    -0.07
    gre
    -0.07
    æľ¨çĵľ
    -0.07
    æĽ¾ä»»èģĮ
    -0.07
     Morales
    -0.07
    iris
    -0.07
    éĨīäºĨ
    -0.07
    cran
    -0.06
    ç©¿è¶Ĭ
    -0.06
    POSITIVE LOGITS
    èĩªçĦ¶çķĮ
    0.08
    çĬ¶æĢģçļĦ
    0.07
    ogan
    0.07
     reag
    0.07
    -state
    0.07
    éĢ¸
    0.07
     Warta
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
     нака
    0.07
    çĬ¶æħĭãģ§
    0.07
    Activations Density 0.010%

    No Known Activations