© 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. 22574
    Prev
    Next
    INDEX
    Explanations

    heuristic and algorithms

    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
    æī¿è½½
    -0.09
    watan
    -0.09
    ereal
    -0.08
    衬
    -0.08
    .Abs
    -0.08
    cope
    -0.08
    mux
    -0.08
    Platforms
    -0.08
    为载ä½ĵ
    -0.08
    åħ¥åij³
    -0.08
    POSITIVE LOGITS
    ç®Ĺæ³ķ
    0.11
     algorithm
    0.11
     greedy
    0.11
     algorithms
    0.10
     priorit
    0.10
     based
    0.10
     heuristic
    0.10
     Algorithm
    0.10
     random
    0.09
     criteria
    0.09
    Activations Density 0.056%

    No Known Activations