© 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. 23881
    Prev
    Next
    INDEX
    Explanations

    English words

    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
     newly
    -0.07
    бла
    -0.07
    ahlen
    -0.07
     bestowed
    -0.06
     Freib
    -0.06
     reto
    -0.06
     proceeds
    -0.06
    ium
    -0.06
     Unless
    -0.06
    IPH
    -0.06
    POSITIVE LOGITS
    edur
    0.08
    æīĢ以对äºİ
    0.08
    æīĢæľīçļĦ
    0.08
    çĨĦçģ«
    0.07
    以èĩªå·±çļĦ
    0.07
    åĥıä½ł
    0.07
    @author
    0.07
    umpt
    0.07
    ancia
    0.07
    ideon
    0.07
    Activations Density 0.009%

    No Known Activations