© 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. 13200
    Prev
    Next
    INDEX
    Explanations

    Continue reading

    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
    icode
    -0.07
     ãĤ¹ãĥĿãĥ³ãĤµãĥ¼ãĤµãĤ¤ãĥĪ
    -0.07
    ]:=
    -0.07
    warts
    -0.07
    rokes
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    ftime
    -0.07
    çģµ
    -0.07
     snap
    -0.06
    ipo
    -0.06
    POSITIVE LOGITS
    以ä¸ĬåĨħ容
    0.07
    æıīäºĨæıī
    0.07
    çĥŃéŨæłĩçŃ¾
    0.07
    LAST
    0.06
    OUCH
    0.06
    izat
    0.06
    à¸Ĭัà¸Ķ
    0.06
    <tool_response>
    0.06
    tori
    0.06
     anything
    0.06
    Activations Density 0.324%

    No Known Activations