© 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. 43066
    Prev
    Next
    INDEX
    Explanations

    code snippets or tags

    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
    nger
    -0.07
    lator
    -0.07
    ÅĤoż
    -0.07
    eraus
    -0.06
     similar
    -0.06
    åł¡
    -0.06
    çĥŁ
    -0.06
    enan
    -0.06
    类似
    -0.06
    reno
    -0.06
    POSITIVE LOGITS
    éĩįçĤ¹æĺ¯
    0.08
    ufs
    0.07
    ÙĦاس
    0.07
    ibi
    0.07
    ieb
    0.07
    并请
    0.07
    nj
    0.07
    .acquire
    0.07
    erte
    0.07
    unj
    0.06
    Activations Density 0.240%

    No Known Activations