© 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. 20-TRANSCODER-HP
    7. 107095
    Prev
    Next
    INDEX
    Explanations

    Periods

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     tolerant
    -0.27
     opinion
    -0.26
     interests
    -0.26
    -treated
    -0.25
     unanimous
    -0.24
    *[
    -0.24
     invariant
    -0.24
    æĺ¯æ²¡æľī
    -0.23
     treat
    -0.23
    vore
    -0.23
    POSITIVE LOGITS
    èĢ»
    0.25
    åı°
    0.25
     theirs
    0.25
    ä½ĵçİ°
    0.24
    èĩªå·±çļĦ
    0.24
    鸳
    0.24
    owns
    0.23
    биÑĤ
    0.23
    col
    0.23
    adem
    0.23
    Activations Density 2.751%

    No Known Activations