© 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. 23-TRANSCODER-HP
    7. 24447
    Prev
    Next
    INDEX
    Explanations

    and, comma

    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
    utations
    -0.28
    OLDER
    -0.28
    sthrough
    -0.26
    å®ĺ宣
    -0.26
    .Fat
    -0.24
    ieber
    -0.24
    fov
    -0.24
     provincial
    -0.24
    lients
    -0.24
     enjoying
    -0.24
    POSITIVE LOGITS
     a
    0.30
    èĹ»
    0.29
    ä¸ĢæĬĬ
    0.29
    æī¼
    0.28
     mention
    0.28
    ä¸Ģ个
    0.28
     number
    0.28
     numerator
    0.28
     whether
    0.27
     amount
    0.27
    Activations Density 0.008%

    No Known Activations