© 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. 19139
    Prev
    Next
    INDEX
    Explanations

    derivatives and precursors

    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
    å°ı人
    -0.06
    ase
    -0.06
    ymb
    -0.06
    nad
    -0.06
    æ¯ıç»Ħ
    -0.06
    uz
    -0.05
    oda
    -0.05
    uchar
    -0.05
    abe
    -0.05
    thur
    -0.05
    POSITIVE LOGITS
    ingar
    0.06
    rans
    0.06
    å¾ĢæľŁç²¾å½©
    0.06
    å¸Ĥ人æ°ijæ³ķéĻ¢
    0.06
    ipan
    0.05
    kait
    0.05
    ensif
    0.05
     inject
    0.05
    IRON
    0.05
    ijnen
    0.05
    Activations Density 0.082%

    No Known Activations