© 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. 18840
    Prev
    Next
    INDEX
    Explanations

    up to you

    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
    åı·
    -0.06
    rew
    -0.05
    èĻŁ
    -0.05
    åı·çļĦ
    -0.05
    æį¢
    -0.05
    information
    -0.05
    ¦
    -0.05
     Typ
    -0.05
    ç¡®
    -0.04
    info
    -0.04
    POSITIVE LOGITS
    tera
    0.07
    rš
    0.06
    lings
    0.06
    UIT
    0.06
    ipt
    0.06
    elman
    0.06
    heimer
    0.06
    landers
    0.06
    AIL
    0.06
    eltas
    0.06
    Activations Density 0.002%

    No Known Activations