© 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. 21792
    Prev
    Next
    INDEX
    Explanations

    ranges of zero to

    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
    format
    -0.05
    ife
    -0.05
    çļĦ主è¦ģéĹ®é¢ĺ
    -0.05
    磫
    -0.05
     Freak
    -0.05
    çļĦ主è¦ģ
    -0.05
    度è¿ĩ
    -0.04
    çļĦéĩįçĤ¹
    -0.04
     freak
    -0.04
    ij
    -0.04
    POSITIVE LOGITS
    oran
    0.07
    èĮħ
    0.06
    stin
    0.06
    çŁ¢
    0.06
    è¡ĢçļĦ
    0.06
    komm
    0.06
    çŃĶ
    0.06
    ä»»ä½ķæŶåĢĻ
    0.06
    boro
    0.06
    inthians
    0.06
    Activations Density 0.003%

    No Known Activations