© 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. 13765
    Prev
    Next
    INDEX
    Explanations

    fine tuning, hierarchy, principle, Dream Pop, Speedmaster

    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
    itore
    -0.08
    ernet
    -0.08
     typeof
    -0.08
    engang
    -0.08
    æŬ
    -0.07
    ãĥķãĥ«
    -0.07
     domicili
    -0.07
    ç§Ģæīį
    -0.07
    çī¹æľĹ
    -0.07
    è°Ĭ
    -0.07
    POSITIVE LOGITS
     cosm
    0.09
    å·§åIJĪ
    0.07
    è°ľé¢ĺ
    0.07
     cosmic
    0.07
    åĩij
    0.07
    Reset
    0.07
     Lottery
    0.07
    人为
    0.07
     Suicide
    0.07
     puzzles
    0.07
    Activations Density 0.009%

    No Known Activations