© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17687
    Prev
    Next
    INDEX
    Explanations

    frameworks

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    หà¸Ļ
    -0.05
    ering
    -0.05
    eners
    -0.05
    ادت
    -0.05
    aves
    -0.05
    èĦijçŃĭ
    -0.05
     grouping
    -0.05
    åĽ¢
    -0.05
    itas
    -0.05
    arding
    -0.05
    POSITIVE LOGITS
    ãģĤãĤĮãģ°
    0.07
    saus
    0.06
    iese
    0.06
    outlined
    0.06
     frameworks
    0.06
    èī²åĪĹ
    0.06
    UGH
    0.06
    æĪĸ以ä¸Ĭ
    0.06
     seul
    0.06
    áss
    0.06
    Activations Density 0.006%

    No Known Activations