© 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. 17968
    Prev
    Next
    INDEX
    Explanations

    ISBNs or identifiers

    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
     *
    -0.05
    иÑģ
    -0.05
    vers
    -0.05
    anto
    -0.05
    Äĥ
    -0.05
     cf
    -0.05
     whe
    -0.05
     handling
    -0.04
     fin
    -0.04
    iÅŁ
    -0.04
    POSITIVE LOGITS
    thern
    0.06
    çħŀ
    0.06
     Dont
    0.06
    gie
    0.06
    åĬłæĭ¿å¤§
    0.06
     hÃłi
    0.06
    dont
    0.06
    ä¸įçĿĢ
    0.06
    åİ®
    0.06
    å°ĨçIJĥ
    0.06
    Activations Density 0.216%

    No Known Activations