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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 5862
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pressor
    -0.34
    pressed
    -0.28
    ypress
    -0.27
    ossip
    -0.26
    /MPL
    -0.26
    anness
    -0.26
    GENCY
    -0.25
     Cron
    -0.25
    esome
    -0.24
    aska
    -0.24
    POSITIVE LOGITS
    ç§ĥ
    0.29
    æħĭ
    0.27
    hound
    0.27
    ç£ķ
    0.27
    å®ļ
    0.26
    æľīåĩłä¸ª
    0.26
    éģĵè·¯ä¸Ĭ
    0.25
    EQUAL
    0.24
    å½ĵåľ°çļĦ
    0.24
    Ä·
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.