© 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. 41858
    Prev
    Next
    INDEX
    Explanations

    reduce prices

    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
    _CONTINUE
    -0.08
    athon
    -0.08
    upp
    -0.08
     Ria
    -0.07
     troublesome
    -0.07
    proc
    -0.07
    好å¿ĥ
    -0.07
    SCORE
    -0.07
     ìĺģ
    -0.07
    asseur
    -0.07
    POSITIVE LOGITS
     individual
    0.12
     Individual
    0.12
    åįķ个
    0.11
    åѤ
    0.11
     ê°ľë³Ħ
    0.10
    Individual
    0.10
     individually
    0.10
    individual
    0.10
    _individual
    0.10
     individuales
    0.10
    Activations Density 0.183%

    No Known Activations