© 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. 41505
    Prev
    Next
    INDEX
    Explanations

    number of solutions, steps, moves

    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
    _MATH
    -0.09
    utsch
    -0.08
    horn
    -0.08
    INGER
    -0.08
    رائ
    -0.08
    aset
    -0.08
    emento
    -0.07
    bergen
    -0.07
    UAR
    -0.07
    èĢ³çĽ®
    -0.07
    POSITIVE LOGITS
    æľĢéķ¿çļĦ
    0.08
    æį·
    0.07
    æľĢçŁŃ
    0.07
    æľĢå°ij
    0.07
    åĨ¤æŀī
    0.07
    ä¼IJ
    0.07
    å®ĮæĪIJ
    0.07
    å°ijäºİ
    0.07
    é«ĺæķĪçļĦ
    0.07
    mins
    0.07
    Activations Density 0.007%

    No Known Activations