© 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. 33-TRANSCODER-HP
    7. 53255
    Prev
    Next
    INDEX
    Explanations

    professions ending in "ers"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    odynam
    -0.29
    been
    -0.28
    _that
    -0.28
    ä»ĸæĽ¾
    -0.26
    IfExists
    -0.26
     bahwa
    -0.26
    Was
    -0.26
    ä½ıå®ħ
    -0.26
    _was
    -0.25
     rằng
    -0.25
    POSITIVE LOGITS
     stated
    0.36
     at
    0.34
     maintained
    0.33
     watched
    0.33
     felt
    0.32
     sought
    0.32
     listened
    0.32
     insist
    0.32
     demonstrated
    0.31
     understood
    0.31
    Activations Density 0.064%

    No Known Activations