© 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. 21563
    Prev
    Next
    INDEX
    Explanations

    verbs of speech

    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
    erschein
    -0.06
    éĹªåħīçĤ¹
    -0.06
     restrictive
    -0.06
    armo
    -0.05
     venit
    -0.05
     mirrored
    -0.05
    שר
    -0.05
    家家
    -0.05
    æĭĭ
    -0.05
    èĢģé¹°
    -0.05
    POSITIVE LOGITS
    æĺķ
    0.06
    amer
    0.06
    olis
    0.06
    unek
    0.05
    ï¼ļ“
    0.05
    ubu
    0.05
    Note
    0.05
    notes
    0.05
    nie
    0.05
    uler
    0.05
    Activations Density 0.004%

    No Known Activations