© 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. 18-TRANSCODER-HP
    7. 88354
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_18.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.18.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     turnover
    -0.27
    isable
    -0.27
     d
    -0.26
    angelo
    -0.26
    _quality
    -0.25
    å·¥ä½ľæķĪçİĩ
    -0.24
     Fritz
    -0.24
    éĺī
    -0.24
    åIJĽ
    -0.24
    Qual
    -0.23
    POSITIVE LOGITS
    èĥĻ
    0.27
    idge
    0.27
     zro
    0.25
    ç´¯äºĨ
    0.25
    lider
    0.25
    oncé
    0.25
    åĨħåľ°
    0.25
     heck
    0.25
    éĻįèIJ½
    0.25
    pit
    0.24
    Activations Density 2.382%

    No Known Activations