© 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. 18894
    Prev
    Next
    INDEX
    Explanations

    grouping words

    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
    uko
    -0.05
    2
    -0.05
    d
    -0.05
    æķĪåºĶ
    -0.05
    åĪĨæѧ
    -0.05
     abre
    -0.05
    å°½
    -0.05
    alh
    -0.05
     rud
    -0.05
    éĥ¨åĪĨ
    -0.05
    POSITIVE LOGITS
    izz
    0.07
    awan
    0.06
    estos
    0.06
    ä¸Ĭæ·»
    0.06
    cé
    0.06
    etur
    0.06
    ripper
    0.06
    iterate
    0.06
    æĹ¥ä»¥
    0.06
    åĬŀçIJĨæµģç¨ĭ
    0.06
    Activations Density 0.019%

    No Known Activations