© 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. 41660
    Prev
    Next
    INDEX
    Explanations

    amorphous, negotiate, crystals, hearing loss

    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
    emel
    -0.07
     Spy
    -0.06
    éĩĮåħĭ
    -0.06
    .target
    -0.06
     Webb
    -0.06
     slippery
    -0.05
    ÙĬا
    -0.05
     span
    -0.05
    arra
    -0.05
    çĪ±ä¸į
    -0.05
    POSITIVE LOGITS
    wier
    0.09
    ারণ
    0.08
    _TA
    0.08
    acto
    0.08
     finally
    0.08
    serviceName
    0.07
    æľĢç»Ī以
    0.07
    stown
    0.07
    ultat
    0.07
     nasib
    0.07
    Activations Density 0.039%

    No Known Activations