© 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. 34335
    Prev
    Next
    INDEX
    Explanations

    Majority votes

    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
    ูล
    -0.08
    çĻ¾åħĥ
    -0.08
    å¯Įæ°ij
    -0.07
    fertig
    -0.07
    ardi
    -0.07
    onge
    -0.07
    îte
    -0.07
    atika
    -0.07
    emar
    -0.07
    itra
    -0.07
    POSITIVE LOGITS
    åįĬæķ°
    0.11
     Majority
    0.11
     majority
    0.10
     votes
    0.10
     voting
    0.10
     vote
    0.10
    表åĨ³
    0.09
    vote
    0.09
    votes
    0.09
     outnumber
    0.08
    Activations Density 0.041%

    No Known Activations