© 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. 7685
    Prev
    Next
    INDEX
    Explanations

    descriptive words for objects or attributes

    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
    itr
    -0.07
    оÑĢÑĤи
    -0.07
    kit
    -0.07
    antz
    -0.07
     disqualified
    -0.07
    orto
    -0.06
    å½ĵå±ŀ
    -0.06
     definitiv
    -0.06
    çĪĽ
    -0.06
    åĽŀåİ»åIJ§
    -0.06
    POSITIVE LOGITS
    resse
    0.08
    icens
    0.08
    adÃŃ
    0.07
     means
    0.07
    means
    0.07
    æĦıåij³çĿĢ
    0.07
     acu
    0.07
    onnier
    0.07
    çī¹æľīçļĦ
    0.07
    lée
    0.07
    Activations Density 0.119%

    No Known Activations