© 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. 41805
    Prev
    Next
    INDEX
    Explanations

    50mm, step length, Red Bull Ring

    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
    .Values
    -0.07
    ottom
    -0.07
    åīįåįģåIJį
    -0.07
    ager
    -0.07
    æį¶
    -0.07
    Ross
    -0.07
    иÑģÑĤо
    -0.07
    вÑĤо
    -0.07
    agers
    -0.07
    ervals
    -0.06
    POSITIVE LOGITS
    geführt
    0.07
    æ±Łå¤ı
    0.07
    ADED
    0.07
    éģĵ人
    0.07
    ove
    0.07
    igy
    0.07
    umul
    0.07
    ÙĪسة
    0.07
     BÃģ
    0.07
    exter
    0.07
    Activations Density 0.714%

    No Known Activations