© 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. 27471
    Prev
    Next
    INDEX
    Explanations

    vs and against

    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
    rega
    -0.07
    rex
    -0.07
    å±ħ
    -0.07
    rego
    -0.07
    дев
    -0.06
    εÏģι
    -0.06
    ä¸İåİŁ
    -0.06
     Binder
    -0.06
    åıijå±ķä¸İ
    -0.06
    ä¸Ģä½ĵ
    -0.06
    POSITIVE LOGITS
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    ØŃاÙħ
    0.08
    amac
    0.07
    GestureRecognizer
    0.07
    æĪĺä¸Ń
    0.07
    以任ä½ķ
    0.07
    веÑĢÑĪен
    0.07
     policemen
    0.06
    ãĥİãĥ³
    0.06
    çĻ¾éĩĮ
    0.06
    Activations Density 0.094%

    No Known Activations