© 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. 20-TRANSCODER-HP
    7. 106914
    Prev
    Next
    INDEX
    Explanations

    Instructions or suggestions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    anel
    -0.27
    ä¸ĭ车
    -0.26
     sout
    -0.26
    chine
    -0.26
     blazing
    -0.25
    amic
    -0.25
    stre
    -0.25
    èĩ»
    -0.25
    åĪĩ
    -0.25
    èĤī
    -0.25
    POSITIVE LOGITS
    study
    0.28
     study
    0.26
    Studies
    0.26
    иÑĤеÑĤ
    0.25
     infl
    0.25
    Attempt
    0.25
    =np
    0.24
    _CONN
    0.24
    _study
    0.24
    out
    0.23
    Activations Density 20.136%

    No Known Activations