© 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. 163020
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    cket
    -0.26
    -Trump
    -0.26
    ibaba
    -0.26
    æ¶Īè´¹åįĩ级
    -0.26
    phia
    -0.25
    Together
    -0.25
     sympath
    -0.25
    pha
    -0.25
     minecraft
    -0.24
    uki
    -0.24
    POSITIVE LOGITS
    æĹ©çĤ¹
    0.27
    ÑĢин
    0.27
    OW
    0.27
     married
    0.26
    缩çŁŃ
    0.26
    templates
    0.24
     stocks
    0.24
    _templates
    0.24
    Html
    0.24
    auto
    0.23
    Activations Density 0.017%

    No Known Activations

    This feature has no known activations.