© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 7370
    Prev
    Next
    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    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
    qc
    -0.27
    rpc
    -0.24
    typ
    -0.24
    orrar
    -0.24
     Caucus
    -0.24
     undue
    -0.24
    ongyang
    -0.23
    ismatic
    -0.23
    abby
    -0.23
    å¸¦ä½ł
    -0.23
    POSITIVE LOGITS
    chen
    0.29
    olon
    0.28
    chal
    0.26
    ä¹Łè®©
    0.26
    ------↵
    0.26
     DIG
    0.25
     Digest
    0.24
    äºĨæĪijçļĦ
    0.24
    åĪ°äºĨ
    0.23
    /pass
    0.23
    Activations Density 0.012%

    No Known Activations