© 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. 20755
    Prev
    Next
    INDEX
    Explanations

    movement towards a position or goal

    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
    depend
    -0.06
    ervas
    -0.05
    綴
    -0.05
    çļĦåľ°æĸ¹
    -0.05
    ä¸įåħ¥
    -0.05
     impact
    -0.05
     fate
    -0.05
    kip
    -0.05
     Expanded
    -0.05
     impacts
    -0.05
    POSITIVE LOGITS
    顯示
    0.07
     gradually
    0.06
     shortest
    0.06
    缮æłĩæĺ¯
    0.06
    IGE
    0.06
     slowly
    0.06
    AIT
    0.06
    éĢIJæ¸IJæĪIJ为
    0.06
    å·²ä¹ħ
    0.06
    è¿ŁæĹ©
    0.06
    Activations Density 0.021%

    No Known Activations