© 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. 162886
    Prev
    Next
    INDEX
    Explanations

    by

    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
     shortest
    -0.28
    due
    -0.27
    åĽłä¸ºå®ĥ
    -0.27
     Begins
    -0.27
     både
    -0.27
    åĿıäºĭ
    -0.26
     vaguely
    -0.26
    åIJĥäºı
    -0.25
     resumes
    -0.25
     disastr
    -0.25
    POSITIVE LOGITS
     using
    0.31
    odb
    0.30
     applying
    0.29
     adjusting
    0.28
    using
    0.28
     appending
    0.28
    åĥı
    0.27
    iders
    0.27
    orting
    0.27
    çĶ±
    0.27
    Activations Density 0.027%

    No Known Activations