© 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. 28002
    Prev
    Next
    INDEX
    Explanations

    positional constraints

    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
    æ§Ľ
    -0.08
    éĩİåħ½
    -0.07
    akis
    -0.07
    èĤł
    -0.07
    çķĮ
    -0.06
    veys
    -0.06
    ç»´
    -0.06
    loff
    -0.06
    °
    -0.06
    两ä¸ī
    -0.06
    POSITIVE LOGITS
    æݨçIJĨ
    0.09
    æݨæĸŃ
    0.09
     deductions
    0.09
     contradictions
    0.08
     deduct
    0.08
     positional
    0.08
    timeline
    0.08
    交çĶµ
    0.08
    _constraints
    0.08
     Constraints
    0.08
    Activations Density 0.010%

    No Known Activations