© 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. 27223
    Prev
    Next
    INDEX
    Explanations

    magnitude, call, Northwestern, Pain, Trump, cushions

    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
    ÑĬÑĤ
    -0.09
    åħ¬åı¸å¯¹
    -0.08
    åħ¬åı¸åIJij
    -0.08
    amon
    -0.08
    igrations
    -0.08
    åıĹåĪ°äºĨ
    -0.08
    itano
    -0.08
    åħ¬åı¸ä¸İ
    -0.08
     dazu
    -0.08
    åıĹåĪ°
    -0.08
    POSITIVE LOGITS
    /from
    0.13
    为æŃ¢
    0.12
    gether
    0.12
    égard
    0.12
     ÙĪØ¥ÙĦÙī
    0.11
    çĤºæŃ¢
    0.10
    å®ŀå¤Ħ
    0.10
     detriment
    0.09
     extent
    0.09
    çļĦåľ°æŃ¥
    0.09
    Activations Density 0.739%

    No Known Activations