© 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. 28073
    Prev
    Next
    INDEX
    Explanations

    critical importance or sensitivity

    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
     praktis
    -0.08
    unno
    -0.08
    identally
    -0.08
    çĺ¢
    -0.08
    ungan
    -0.08
    ÃŃas
    -0.08
     práct
    -0.08
     handy
    -0.08
    æĪ¿äº§ç¨İ
    -0.08
    LICENSE
    -0.08
    POSITIVE LOGITS
    åħ³ä¹İ
    0.11
    éĩį大
    0.10
    çī¹æ®Ĭ
    0.10
    æ¶īåıĬ
    0.10
    å¦Ĥæ¶īåıĬ
    0.10
    äºĭåħ³
    0.10
     critical
    0.09
    çŃīçī¹æ®Ĭ
    0.09
    éĩįä¸Ńä¹ĭéĩį
    0.09
     sensitive
    0.09
    Activations Density 0.131%

    No Known Activations