© 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. 39030
    Prev
    Next
    INDEX
    Explanations

    functor or objects

    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
    Commission
    -0.08
     Bark
    -0.07
     Pau
    -0.07
     fing
    -0.06
    å¨ĥå¨ĥ
    -0.06
     commission
    -0.06
    éĺħè¯»æľ¬æĸĩ
    -0.06
    çĦ¦
    -0.06
     Commission
    -0.06
    fraction
    -0.06
    POSITIVE LOGITS
     functor
    0.08
     arity
    0.08
    horn
    0.08
    èĦļæīĭæŀ¶
    0.08
     inhabited
    0.08
    aland
    0.08
    èĻı
    0.08
     dér
    0.08
    âĸ·
    0.08
    intros
    0.07
    Activations Density 0.034%

    No Known Activations