© 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. 20246
    Prev
    Next
    INDEX
    Explanations

    check existence or validity

    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
    emann
    -0.05
    ãĤĤãģĹ
    -0.05
    æľīä¸ĭåĪĹæĥħå½¢ä¹ĭä¸ĢçļĦ
    -0.05
    ak
    -0.05
    å°¤
    -0.05
    ikä
    -0.05
    adero
    -0.05
    arak
    -0.05
    ä¹ĭä¸ĭ
    -0.05
    agg
    -0.05
    POSITIVE LOGITS
    uded
    0.06
    éĤ£ä¹Īç®Ģåįķ
    0.06
    вÑĢе
    0.06
    æł¹æį®åħ¶
    0.05
    éľĢè¦ģæł¹æį®
    0.05
     {}:
    0.05
     Tern
    0.05
    æł¹æį®åħ¬åı¸
    0.05
    antine
    0.05
    Courtesy
    0.05
    Activations Density 0.025%

    No Known Activations