© 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. 17346
    Prev
    Next
    INDEX
    Explanations

    Please provide the four lists so I can generate the explanation for the neuron's behavior

    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
    รมาà¸ģ
    -0.06
     Cage
    -0.06
    äºĨä¸Ģåı¥
    -0.06
    arcz
    -0.06
    omatis
    -0.06
    inga
    -0.06
    isiv
    -0.06
    ropp
    -0.06
    zew
    -0.05
    classed
    -0.05
    POSITIVE LOGITS
     temper
    0.05
    å¤ļåľ°
    0.05
    åħ¶ä¸ī
    0.05
    ä¹Ķ
    0.05
     as
    0.05
     Jou
    0.05
    æľīåĪ©
    0.05
    suit
    0.05
     et
    0.04
    dad
    0.04
    Activations Density 0.040%

    No Known Activations