© 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. 20753
    Prev
    Next
    INDEX
    Explanations

    not found or didn't exist

    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
    åĽłä¸ºè¿ĻäºĽ
    -0.06
    è¦ģéĿł
    -0.06
    olari
    -0.06
    utions
    -0.06
    ails
    -0.06
    æĭįåĪ°
    -0.06
    clam
    -0.06
    viz
    -0.06
    লà§ĩà¦ĸ
    -0.06
    akk
    -0.06
    POSITIVE LOGITS
    ä¸ĬåĬł
    0.05
    åıĪå¦Ĥä½ķ
    0.05
     add
    0.05
    wok
    0.05
    ä¸Ģç³»åĪĹ
    0.05
    ä¸Ģç³»åĪĹçļĦ
    0.05
    æķħæĦı伤害
    0.05
     ageing
    0.04
     followed
    0.04
    ix
    0.04
    Activations Density 0.012%

    No Known Activations