© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20085
    Prev
    Next
    INDEX
    Explanations

    directory or folder

    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
     careless
    -0.07
    änner
    -0.06
    embr
    -0.06
    个åŃĹ
    -0.06
    unid
    -0.06
     cél
    -0.06
    åłĤåłĤ
    -0.06
    _ident
    -0.06
    arra
    -0.06
    åħ¶äº§åĵģ
    -0.06
    POSITIVE LOGITS
    å¸Ĥåľº
    0.05
    ç®Ĺ
    0.05
    è·¯ä¸Ĭ
    0.05
    steen
    0.05
     poni
    0.05
     stav
    0.05
    æľĽ
    0.05
    rien
    0.04
    æĤ£
    0.04
    æű
    0.04
    Activations Density 0.015%

    No Known Activations