© 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. 18450
    Prev
    Next
    INDEX
    Explanations

    making lists of things

    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
    ebed
    -0.07
    ä¼ģä¸ļ管çIJĨåĴ¨è¯¢
    -0.06
     Filoso
    -0.06
    stime
    -0.06
    ä¸ĵæĪ·
    -0.06
    è§ī
    -0.06
     Berm
    -0.06
    ebet
    -0.06
    è¶Ł
    -0.06
     Maine
    -0.06
    POSITIVE LOGITS
    Âł
    0.06
    lee
    0.05
     instead
    0.05
    h
    0.05
    plet
    0.05
    ix
    0.05
    om
    0.05
    g
    0.05
    å®ī
    0.05
    kar
    0.05
    Activations Density 0.008%

    No Known Activations