© 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. 22-TRANSCODER-HP
    7. 98956
    Prev
    Next
    INDEX
    Explanations

    Vulgar language/negative sentiment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    imson
    -0.24
    åĸī
    -0.23
     bufferSize
    -0.23
     hone
    -0.23
    PCS
    -0.23
     recurrent
    -0.23
    npj
    -0.22
    thus
    -0.22
    èĦIJ
    -0.22
    èĽĨ
    -0.22
    POSITIVE LOGITS
     Âł Âł Âł Âł
    0.28
    ³³³³³³³³
    0.28
    ìłĢ
    0.26
    -no
    0.26
    sock
    0.26
     really
    0.26
     Âł Âł
    0.26
    ives
    0.26
    Âł
    0.25
    èĢĹ
    0.25
    Activations Density 0.134%

    No Known Activations