© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 22279
    Prev
    Next
    INDEX
    Explanations

    he was appointed

    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
    çĿĢåĬĽæīĵéĢł
    -0.07
    -gay
    -0.06
    eldorf
    -0.06
    Ïģκ
    -0.06
     Aeropuerto
    -0.06
    erville
    -0.06
    @$
    -0.06
     ('$
    -0.06
    esm
    -0.06
    åĩºæĿ¥ãģ¾ãģĹãģŁ
    -0.06
    POSITIVE LOGITS
    è¿«
    0.05
    满足
    0.05
    æ¦Ĥæĭ¬
    0.05
    åĽł
    0.05
    gado
    0.05
    åīį
    0.05
    åĪ»
    0.05
    penas
    0.05
    çİĩ
    0.05
    é¼ĵèµ·
    0.05
    Activations Density 0.108%

    No Known Activations