© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2414
    Prev
    Next
    INDEX
    Explanations

    building walls and enclosures

    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
    èįī丼
    -0.08
     ÐĶиамеÑĤ
    -0.08
    åħ¬å®³
    -0.07
    åħ¬æŃ£
    -0.07
    rita
    -0.07
    bron
    -0.07
    éķĬ
    -0.07
    å®ļçĤ¹
    -0.07
    alty
    -0.06
    书çŃ¾
    -0.06
    POSITIVE LOGITS
    å¢Ļä½ĵ
    0.11
     walls
    0.10
    éĩĩåħī
    0.10
     architectural
    0.09
     exterior
    0.09
     residential
    0.09
    éĩĩæļĸ
    0.09
    主åį§
    0.09
    æī¿éĩį
    0.09
    建çŃijéĿ¢ç§¯
    0.09
    Activations Density 0.267%

    No Known Activations