© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161912
    Prev
    Next
    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    antine
    -0.29
    åĪĻ
    -0.28
    cht
    -0.28
    ulating
    -0.27
    平衡
    -0.26
    ulent
    -0.26
    éļĶ
    -0.25
    flow
    -0.25
    cast
    -0.24
     rằng
    -0.24
    POSITIVE LOGITS
    éĢģåĩº
    0.30
    éĢģæĿ¥
    0.29
    ĶåĽŀ
    0.28
     shortcomings
    0.26
    ,eg
    0.26
    thro
    0.25
     share
    0.25
    rolled
    0.25
    ounder
    0.25
     pigeon
    0.25
    Activations Density 0.023%

    No Known Activations