© 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. 20729
    Prev
    Next
    INDEX
    Explanations

    continuous actions

    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
    tret
    -0.06
    ä¼ģ
    -0.06
     amt
    -0.06
    ÅĪa
    -0.06
    æıIJ
    -0.06
    Autom
    -0.06
    觸
    -0.06
     gut
    -0.06
    ingar
    -0.06
    ütte
    -0.05
    POSITIVE LOGITS
     Continuous
    0.07
    oy
    0.06
    continuous
    0.06
    Continuous
    0.06
     continuous
    0.06
     Dip
    0.05
    æºIJæºIJ
    0.05
    éĩįåıł
    0.05
    çĬ¶æĢģ
    0.05
    hour
    0.05
    Activations Density 0.004%

    No Known Activations