© 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. 8087
    Prev
    Next
    INDEX
    Explanations

    convergent sequence

    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
    deo
    -0.07
    åħ°çī¹
    -0.07
     cigaret
    -0.07
    quil
    -0.07
    usura
    -0.07
     пÑĢез
    -0.07
    ä¸įæĸ¹ä¾¿
    -0.07
    çĶµå½±ä¸Ń
    -0.07
    éĺ´éĺ³
    -0.07
    éĩįè¦ģçļĦäºĭæĥħ
    -0.07
    POSITIVE LOGITS
     infinite
    0.07
    çķĮéĻIJ
    0.07
    æī©å±ķåĪ°
    0.07
     radius
    0.07
    ä¸ĭéĻIJ
    0.07
    uas
    0.07
    finite
    0.07
     внÑĥÑĤÑĢÑĮ
    0.07
     Bound
    0.07
    åįĬå¾Ħ
    0.07
    Activations Density 0.005%

    No Known Activations