© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 19-TRANSCODER-HP
    7. 9338
    Prev
    Next
    INDEX
    Explanations

    Parentheses and quotations

    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
    ognito
    -0.28
    -che
    -0.27
    ouch
    -0.27
    icina
    -0.25
     Christie
    -0.24
    eled
    -0.24
    iceps
    -0.24
    bei
    -0.24
    ivers
    -0.24
    elu
    -0.24
    POSITIVE LOGITS
     Duterte
    0.28
    eree
    0.28
    oning
    0.26
    âݤ
    0.26
    å°Ŀ
    0.24
    ForObject
    0.24
    hints
    0.23
    éĴĿ
    0.23
    å¾µ
    0.23
    è¡Į为
    0.23
    Activations Density 0.053%

    No Known Activations