© 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. 20312
    Prev
    Next
    INDEX
    Explanations

    asp.net, renal, ergotamine, links, registers

    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
    su
    -0.06
    許
    -0.05
    estra
    -0.05
     Desert
    -0.05
     su
    -0.05
    çĶŁçĶŁ
    -0.05
    ut
    -0.05
    许
    -0.05
     aforementioned
    -0.05
    por
    -0.05
    POSITIVE LOGITS
    ander
    0.06
    teil
    0.06
     apos
    0.06
    ÑĢга
    0.05
    rame
    0.05
    澳洲
    0.05
    å½¼æѤ
    0.05
    kis
    0.05
    tick
    0.05
    ipline
    0.05
    Activations Density 0.035%

    No Known Activations