© 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. 39164
    Prev
    Next
    INDEX
    Explanations

    halogen and halogenated compounds

    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
    ercial
    -0.07
    нÑıм
    -0.07
    nev
    -0.07
    nten
    -0.06
    lius
    -0.06
    nie
    -0.06
    cimento
    -0.06
     unm
    -0.06
    iramente
    -0.06
    cimiento
    -0.06
    POSITIVE LOGITS
    ination
    0.09
    ász
    0.08
    ìį¨
    0.08
    биÑĢ
    0.08
     Gda
    0.08
    ħ§
    0.08
    εί
    0.07
    å¸ĥæĸ¯
    0.07
    asting
    0.07
    anth
    0.07
    Activations Density 0.006%

    No Known Activations