© 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. 18510
    Prev
    Next
    INDEX
    Explanations

    word suffixes like D-, M-, s-, F-, K-, c-, M-, P-, G-

    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
    evol
    -0.06
    orough
    -0.06
    emblée
    -0.06
    theless
    -0.06
    ëĭ¤ëĬĶ
    -0.06
    eed
    -0.06
    «
    -0.06
    âĢ¢
    -0.06
    åģļå¤ļ
    -0.06
    oke
    -0.05
    POSITIVE LOGITS
    ãĥ³
    0.08
    Ùĩ
    0.07
    ÙĬØ©
    0.07
    iode
    0.07
    ت
    0.07
    æľī
    0.07
    iad
    0.06
    ÙĤص
    0.06
    iou
    0.06
    en
    0.06
    Activations Density 0.152%

    No Known Activations