© 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. 17198
    Prev
    Next
    INDEX
    Explanations

    postal code and RFC identifier

    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
    ÑģÑĤеÑģÑĤвенно
    -0.06
     dags
    -0.06
    åį³çĶ¨
    -0.06
     saada
    -0.06
    ड़ा
    -0.06
    åľ¨ç¬¬
    -0.06
    ÑĢид
    -0.06
    çĶ±çľģ
    -0.05
     tutv
    -0.05
     saper
    -0.05
    POSITIVE LOGITS
    æĺ¯éĿŀ
    0.07
    boro
    0.06
     analytical
    0.06
    stra
    0.06
    abr
    0.05
    è¾ĸ
    0.05
    ä¸īä¸ĸ
    0.05
    abee
    0.05
    ä¸Ģäºĭ
    0.05
    jev
    0.05
    Activations Density 0.006%

    No Known Activations