© 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. 25613
    Prev
    Next
    INDEX
    Explanations

    character followed by number

    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
    åĩ¯è¿ª
    -0.08
    atici
    -0.07
     Recu
    -0.07
    <|box_end|>
    -0.07
    å®Ļ
    -0.07
    æ½Ń
    -0.07
     برÙĬ
    -0.07
    ali
    -0.07
    Bru
    -0.07
     recru
    -0.07
    POSITIVE LOGITS
    maak
    0.07
    om
    0.07
    åķĦ
    0.06
    clave
    0.06
    uator
    0.06
    aksi
    0.06
    çģ¿çĥĤ
    0.06
    cpt
    0.06
    没æ³ķ
    0.06
    åĺĨ
    0.06
    Activations Density 0.002%

    No Known Activations