© 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. 28934
    Prev
    Next
    INDEX
    Explanations

    has been

    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
    ther
    -0.07
    强
    -0.07
    esor
    -0.07
    agher
    -0.07
    OK
    -0.07
     agence
    -0.06
    rise
    -0.06
    ittle
    -0.06
    å°ıå§IJ
    -0.06
    imismo
    -0.06
    POSITIVE LOGITS
    æīĢå±ŀåĪĨç±»
    0.07
    ::$_
    0.07
    çİ°å°±
    0.07
    fes
    0.07
    dings
    0.07
    onsel
    0.07
    ä»İåħ¶
    0.07
    åħ¶çī¹å¾ģåľ¨äºİ
    0.07
    以ä¸ĭç®Ģ称
    0.07
    人åijĺè§Ħ模
    0.07
    Activations Density 0.182%

    No Known Activations