© 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. 4181
    Prev
    Next
    INDEX
    Explanations

    proposal discusses research

    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
    æ¥
    -0.08
    geg
    -0.07
    åĪĨä¹ĭä¸Ģ
    -0.07
    å±Ģåī¯å±Ģéķ¿
    -0.07
    orp
    -0.06
    sk
    -0.06
    owska
    -0.06
    å¾Ĺæīĭ
    -0.06
    erd
    -0.06
    æĥ¬
    -0.06
    POSITIVE LOGITS
    elage
    0.08
    æķ¦
    0.08
    çĻ¾åº¦æIJľç´¢
    0.07
     Esse
    0.07
    åİļå¾·
    0.07
    åĽĽæµ·
    0.07
    å¸ĮæľĽèĥ½å¤Łå¸®åĬ©
    0.07
    ento
    0.07
    å¦Ĥæ¶īåıĬ
    0.07
    ATCH
    0.07
    Activations Density 0.008%

    No Known Activations