© 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. 33627
    Prev
    Next
    INDEX
    Explanations

    unique concept

    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
    缮å®ī
    -0.09
    asil
    -0.07
    abase
    -0.07
    adhan
    -0.07
    åħ¨çº¿
    -0.07
     acte
    -0.07
    ChangeEvent
    -0.07
    æĸ°é£İ
    -0.07
    árov
    -0.07
    rud
    -0.07
    POSITIVE LOGITS
    çī¹æ®ĬçļĦ
    0.16
    ä¹ĭå¤Ħåľ¨äºİ
    0.13
    çī¹æ®Ĭ
    0.13
    çŃīçī¹æ®Ĭ
    0.12
    çĭ¬çī¹çļĦ
    0.12
    çī¹æ®ĬæĢ§
    0.12
     unique
    0.11
     Unique
    0.11
     special
    0.11
    çĭ¬çī¹
    0.11
    Activations Density 0.220%

    No Known Activations