© 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. 32538
    Prev
    Next
    INDEX
    Explanations

    candidate

    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
    szt
    -0.08
    éĩĩ
    -0.07
    anticipated
    -0.07
    quet
    -0.07
    æľīäºĽåľ°æĸ¹
    -0.06
    åįłåĪ°
    -0.06
    StateManager
    -0.06
    羨
    -0.06
    è¨Ī
    -0.06
    angs
    -0.06
    POSITIVE LOGITS
     candidate
    0.14
    åĢĻéĢī
    0.14
    Candidate
    0.13
    candidate
    0.12
     candidates
    0.12
     Candidate
    0.11
     íĽĦë³´
    0.11
    åĢĻéĢī人
    0.11
    å°Ŀè¯ķ
    0.11
     candidat
    0.11
    Activations Density 0.144%

    No Known Activations