© 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. 19-TRANSCODER-HP
    7. 4936
    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
    -repeat
    -0.27
    -ok
    -0.26
    ushing
    -0.25
    å±ħ
    -0.25
    )arg
    -0.25
    åľ°æ¯¯
    -0.24
    =N
    -0.24
    lap
    -0.23
    OLUMNS
    -0.23
     calves
    -0.23
    POSITIVE LOGITS
    abyte
    0.29
     forever
    0.26
     al
    0.25
    çļĦçľ¼ç¥ŀ
    0.24
    éĥ¨
    0.24
     Permanent
    0.24
    emax
    0.24
     mer
    0.23
    /repository
    0.23
     ending
    0.23
    Activations Density 0.018%

    No Known Activations

    This feature has no known activations.