© 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. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 87233
    Prev
    Next
    INDEX
    Explanations

    Past tense/participle verbs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢłæĪIJäºĨ
    -0.30
    è¥Ł
    -0.27
    bildung
    -0.27
    æıIJåįĩäºĨ
    -0.27
    æį¢äºĨ
    -0.27
    举åĬŀäºĨ
    -0.27
     UIF
    -0.27
    å®ļäºĨ
    -0.26
    _was
    -0.26
    æĪIJåIJį
    -0.26
    POSITIVE LOGITS
    s
    0.26
    é¦
    0.26
     pers
    0.26
     perspective
    0.26
     Indian
    0.26
    ns
    0.26
    next
    0.26
    æĪ¿
    0.25
     trans
    0.25
     to
    0.25
    Activations Density 0.030%

    No Known Activations