© 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. 13273
    Prev
    Next
    INDEX
    Explanations

    directed to, see, statements, U, now, declare, past

    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
    究竣
    -0.07
    gress
    -0.07
    atings
    -0.07
     presumably
    -0.06
     Fix
    -0.06
     âĢ¦
    -0.06
     ...,
    -0.06
    ertiary
    -0.06
    anguages
    -0.06
    æŀģ
    -0.06
    POSITIVE LOGITS
    bruck
    0.08
    клада
    0.08
    ammen
    0.07
    ãģłãģŃ
    0.07
    issan
    0.07
    ä¹Łç½¢
    0.07
    rogen
    0.07
    _TEMPLATE
    0.07
    éĻĪ家
    0.07
     téc
    0.07
    Activations Density 0.001%

    No Known Activations