© 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. 19877
    Prev
    Next
    INDEX
    Explanations

    automorphism

    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
    ness
    -0.07
    å®ĥä»¬åľ¨
    -0.06
    vm
    -0.06
    ÙĦاÙħ
    -0.06
    <|box_end|>
    -0.06
    å®īéĢ¸
    -0.06
     venture
    -0.06
     Nu
    -0.06
     sinking
    -0.06
    cratch
    -0.06
    POSITIVE LOGITS
    undas
    0.09
    uckland
    0.08
    aes
    0.08
    scher
    0.08
    unno
    0.08
    _external
    0.08
    argins
    0.07
    ä¿Ŀè´¨
    0.07
    hofer
    0.07
    åĽŃåĨħ
    0.07
    Activations Density 0.009%

    No Known Activations