© 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. 29341
    Prev
    Next
    INDEX
    Explanations

    texts appended with modifications

    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
     infatti
    -0.07
    utz
    -0.07
    å·¥ç¨ĭç³»
    -0.07
    强åĬ²çļĦ
    -0.06
    éĢļè¿ĩå¼Ģå±ķ
    -0.06
    uze
    -0.06
    uh
    -0.06
    ä¸ĸå¤ĸ
    -0.06
    one
    -0.06
    ĸ
    -0.06
    POSITIVE LOGITS
     hopefully
    0.09
    éĢĤå½ĵçļĦ
    0.09
    å°½åı¯èĥ½
    0.08
    èĥ½å¤Łè®©
    0.08
    æĢľ
    0.08
    alion
    0.08
     appropriate
    0.08
    å°½åı¯èĥ½çļĦ
    0.08
    hopefully
    0.07
    jal
    0.07
    Activations Density 0.026%

    No Known Activations