© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19213
    Prev
    Next
    INDEX
    Explanations

    placement and support

    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
    aden
    -0.06
     resultant
    -0.06
    æ»ŀ
    -0.05
     dre
    -0.05
     resultat
    -0.05
    å±ħä½ıçݯå¢ĥ
    -0.05
     congest
    -0.05
    ç»ĵæŀľ
    -0.05
    åģ¥åº·çļĦ
    -0.05
    éĢīä¸Ģ
    -0.05
    POSITIVE LOGITS
    æµģç¨ĭ
    0.06
     boto
    0.06
     gan
    0.06
    aro
    0.06
    Mask
    0.06
    ahoma
    0.06
    åĺ±
    0.06
    acco
    0.06
    ET
    0.06
    تÙħ
    0.05
    Activations Density 0.023%

    No Known Activations