© 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. 19281
    Prev
    Next
    INDEX
    Explanations

    information and advice

    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
    tober
    -0.06
    hab
    -0.06
    ó
    -0.05
    åĵī
    -0.05
    设æĥ³
    -0.05
     supposedly
    -0.05
    inv
    -0.05
    fé
    -0.05
    çªij
    -0.05
     indeed
    -0.05
    POSITIVE LOGITS
     "</
    0.07
    ussen
    0.06
    etet
    0.06
     *</
    0.06
    ÎŃλ
    0.06
    иÑģк
    0.06
    ä¸ĢèĪ¬ä¸º
    0.06
    utschen
    0.06
    ìĦ¬
    0.06
    ëĬIJ
    0.06
    Activations Density 0.002%

    No Known Activations