© 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. 20664
    Prev
    Next
    INDEX
    Explanations

    waterfall or falls

    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
    аÑĨи
    -0.06
    yal
    -0.05
    thin
    -0.05
    overlay
    -0.05
    æµ®
    -0.05
    esame
    -0.05
    ä¸ĬæĿ¥
    -0.05
    recover
    -0.05
    çĶ¨åľ°
    -0.05
    eron
    -0.05
    POSITIVE LOGITS
    çĢijå¸ĥ
    0.08
    åĩºå¤Ħ
    0.06
     waterfall
    0.06
    çĢij
    0.06
    çĮ¿
    0.06
    åĸ·å°Ħ
    0.05
    èĬĤæµģ
    0.05
     casc
    0.05
     trickle
    0.05
     squirt
    0.05
    Activations Density 0.005%

    No Known Activations