© 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. 38087
    Prev
    Next
    INDEX
    Explanations

    is followed by 'found', 'built', 'used', 'easily'

    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
    èĥ½å¤ł
    -0.09
    èĥ½ä¸º
    -0.08
    åı¯ä¾Ľ
    -0.08
    èĥ½å¤Łå°Ĩ
    -0.08
     ability
    -0.08
     pouvoir
    -0.08
    èĥ½å¤Łå¿«éĢŁ
    -0.08
     kunna
    -0.08
    èĥ½å¤Ł
    -0.08
    èĥ½å¤Łåľ¨
    -0.07
    POSITIVE LOGITS
    ’t
    0.11
    çľĭä½ľæĺ¯
    0.10
    't
    0.10
    çIJĨ解为
    0.10
    çľĭä½ľ
    0.09
     easily
    0.09
    ’T
    0.09
    认为æĺ¯
    0.08
     benissimo
    0.08
    aar
    0.08
    Activations Density 0.118%

    No Known Activations