© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21635
    Prev
    Next
    INDEX
    Explanations

    public stock offering

    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
    acea
    -0.07
    æĬ±
    -0.06
    oso
    -0.05
    æĭ¿æĿ¥
    -0.05
    Ùħار
    -0.05
    æĭĴ
    -0.05
     deep
    -0.05
    num
    -0.05
    top
    -0.05
    认å®ļäºĭå®ŀ
    -0.05
    POSITIVE LOGITS
    ennon
    0.06
    éģ¥
    0.06
    á»iji
    0.06
     chromosome
    0.06
    Extern
    0.06
     EXIT
    0.06
    RIEND
    0.06
    velte
    0.05
     naï
    0.05
    erring
    0.05
    Activations Density 0.016%

    No Known Activations