© 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. 18084
    Prev
    Next
    INDEX
    Explanations

    visual representations (images, tables, schematics)

    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
    åĴĮå½±åĵį
    -0.06
    rost
    -0.06
    çļĦè¿ij
    -0.06
    accro
    -0.06
    ibl
    -0.06
    ader
    -0.06
    ÑģÑĤеÑģÑĤвенно
    -0.06
     essayé
    -0.06
    اÙģÙĬ
    -0.06
    Ïĩεία
    -0.06
    POSITIVE LOGITS
    vi
    0.06
    èĤī
    0.05
    注
    0.05
    Nam
    0.05
    æ¢ħæŀĹ
    0.05
    кÑĥ
    0.05
    èĻļ
    0.05
    صاد
    0.05
    si
    0.05
    _const
    0.05
    Activations Density 0.005%

    No Known Activations