© 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. 24906
    Prev
    Next
    INDEX
    Explanations

    calcium phosphate or phosphite salts

    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
    anel
    -0.06
    æŀĹæµ·
    -0.06
    mani
    -0.06
    ä¿Ĭ
    -0.06
     burns
    -0.06
     Sust
    -0.06
    ment
    -0.05
     regular
    -0.05
     involvement
    -0.05
    mind
    -0.05
    POSITIVE LOGITS
    zens
    0.10
    åĪ©çī©
    0.09
    ×ķ׳×Ļ
    0.08
    çĶŁç´ł
    0.08
     Availability
    0.08
    缸çĪ±
    0.08
    upply
    0.08
    éģĩè§ģä½ł
    0.08
    cntl
    0.08
     оÑģа
    0.08
    Activations Density 0.007%

    No Known Activations