© 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. 58598
    Prev
    Next
    INDEX
    Explanations

    hemorrhage

    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
     Klos
    -0.08
    (?)
    -0.08
    /method
    -0.08
    ï¸İ
    -0.08
    æ£ĢæŁ¥ç»Ħ
    -0.08
     babel
    -0.08
    resher
    -0.08
    à¤ĩन
    -0.07
    sworth
    -0.07
    rip
    -0.07
    POSITIVE LOGITS
    æ®Ĩå°½
    0.08
    æĢ§è´«è¡Ģ
    0.08
    ious
    0.07
    æĢ§çĸ¾çĹħ
    0.07
    اء
    0.07
    çĺĢ
    0.07
    æ·ĭæ¼ĵ
    0.07
     pensi
    0.07
    伤
    0.06
    inig
    0.06
    Activations Density 0.036%

    No Known Activations