© 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. 31931
    Prev
    Next
    INDEX
    Explanations

    toxic elements, olive plants

    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
    ul
    -0.06
    ale
    -0.06
    ר×Ĵ
    -0.06
    er
    -0.06
    C
    -0.06
    lev
    -0.06
     partid
    -0.05
     Coimbra
    -0.05
    ahan
    -0.05
    对äºİä¸Ģ个
    -0.05
    POSITIVE LOGITS
    onaut
    0.08
    jad
    0.08
    á»ĥn
    0.08
    icina
    0.08
    schnitt
    0.08
    oref
    0.08
    بÙĥ
    0.08
    isting
    0.08
    ichert
    0.08
    orz
    0.08
    Activations Density 0.018%

    No Known Activations