© 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. 33238
    Prev
    Next
    INDEX
    Explanations

    gold related contexts

    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
    åįĥ家
    -0.09
    gaz
    -0.08
    ãĥ£
    -0.08
    er
    -0.08
    tle
    -0.08
    çĻ¾èįī
    -0.07
    oire
    -0.07
    çIJIJ
    -0.07
    ooter
    -0.07
    ãĥ³ãĤ°
    -0.07
    POSITIVE LOGITS
    smith
    0.13
    çģ¿çģ¿
    0.11
    stone
    0.10
    vern
    0.08
    borough
    0.08
    ä¸įæį¢
    0.08
    mine
    0.08
    rijk
    0.08
    schlä
    0.08
    -hearted
    0.08
    Activations Density 0.030%

    No Known Activations