© 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. 56082
    Prev
    Next
    INDEX
    Explanations

    size of offspring

    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
    richten
    -0.07
    byss
    -0.06
     broader
    -0.06
    åģıå¼±
    -0.06
    atisf
    -0.06
    ARSE
    -0.06
    å¤Ħ级
    -0.06
    ,arr
    -0.06
    posable
    -0.06
    ','','
    -0.06
    POSITIVE LOGITS
    æ¦Ľ
    0.07
    Õ¸ÖĤÕ©
    0.07
    æ¦Ī
    0.07
    åĸµ
    0.07
    ãĥ¼ãĥ«
    0.07
    ¬´
    0.07
    对åħ¶çľŁå®ŀæĢ§è´Łè´£
    0.07
    èıģ
    0.07
    olumn
    0.07
    ola
    0.07
    Activations Density 0.696%

    No Known Activations