© 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. 21037
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    oops
    -0.06
    eranno
    -0.06
    spo
    -0.05
     Ree
    -0.05
    åij¨å¹´çºªå¿µ
    -0.05
    OTOR
    -0.05
    кÑĥпа
    -0.05
    åľ¨ä¸¤
    -0.05
    Ïħμα
    -0.05
    ìķ½ìĿĦ
    -0.05
    POSITIVE LOGITS
    esc
    0.06
     avv
    0.05
    avid
    0.05
    match
    0.05
     match
    0.05
    auj
    0.05
    ciso
    0.05
    ört
    0.05
    ENCE
    0.05
    åı¯èĥ½åıijçĶŁ
    0.05
    Activations Density 0.000%

    No Known Activations