© 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. 61532
    Prev
    Next
    INDEX
    Explanations

    crystallization and precipitation

    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
    olni
    -0.07
    çĥĪçĦ°
    -0.07
     Input
    -0.07
    è¾ĵåħ¥
    -0.07
     quán
    -0.07
    å¤ĩå¿ĺå½ķ
    -0.06
     input
    -0.06
    Input
    -0.06
    åħĥèĢģ
    -0.06
    ared
    -0.06
    POSITIVE LOGITS
    ç»ĵæĻ¶
    0.12
    æŀIJ
    0.11
    æ²īæ·Ģ
    0.11
     precip
    0.10
     crystall
    0.09
     formation
    0.09
     precipitation
    0.09
     orderly
    0.09
    æĻ¶
    0.09
     crystals
    0.09
    Activations Density 0.045%

    No Known Activations