© 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. 23223
    Prev
    Next
    INDEX
    Explanations

    dissolve, dissolution, soluble

    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
     Fast
    -0.07
     fast
    -0.07
    æłijä¸Ĭ
    -0.07
    å®Ī
    -0.07
    èŤ
    -0.07
    å¿«
    -0.06
    çµ
    -0.06
    å¿«çħ§
    -0.06
    çł°
    -0.06
    dom
    -0.06
    POSITIVE LOGITS
    解éļ¾
    0.09
    egov
    0.08
     dissolution
    0.08
    æĶ¶å®¹
    0.08
     dissolve
    0.08
    çĭ¬æłijä¸Ģå¸ľ
    0.08
     soluble
    0.08
    溶
    0.08
    esak
    0.07
    konz
    0.07
    Activations Density 0.002%

    No Known Activations