© 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. 27804
    Prev
    Next
    INDEX
    Explanations

    planes blocking

    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
    墳
    -0.07
    atetime
    -0.06
    å³»
    -0.06
     sleeper
    -0.06
    æīĢå±ķ示
    -0.06
    _unpack
    -0.06
    -0.06
    meer
    -0.06
    housing
    -0.06
    èĢ³çĽ®
    -0.06
    POSITIVE LOGITS
    ç¥ī
    0.09
    夫
    0.08
    zzi
    0.08
    alti
    0.08
    abis
    0.07
     Hij
    0.07
    pera
    0.07
    div
    0.07
    chien
    0.07
    ogo
    0.07
    Activations Density 0.004%

    No Known Activations