© 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. 20912
    Prev
    Next
    INDEX
    Explanations

    etiopathogenic, anti-pattern, intermediate tumors

    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
    erie
    -0.07
    å¼ķ人åħ¥
    -0.07
     "...
    -0.06
    odle
    -0.06
    桦
    -0.06
    -0.06
    æ¼Ĥæµģ
    -0.06
    woord
    -0.06
    ngh
    -0.06
    agg
    -0.06
    POSITIVE LOGITS
     ne
    0.06
    anke
    0.05
    éŨåīį
    0.05
    åĨ²åĬ¨
    0.05
    è¶ĭ
    0.05
     functional
    0.05
     meta
    0.05
    orate
    0.05
    3
    0.05
     Ne
    0.05
    Activations Density 0.030%

    No Known Activations