© 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. 142413
    Prev
    Next
    INDEX
    Explanations

    and or comma

    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
    èģĶç³»çĶµè¯Ŀ
    -0.29
    isses
    -0.26
    åĶ¯ä¸ĢçļĦ
    -0.26
     musica
    -0.26
    Ñĥд
    -0.25
    ients
    -0.25
    .projects
    -0.24
    reet
    -0.24
    åIJ¬è§ģ
    -0.24
    CONTACT
    -0.23
    POSITIVE LOGITS
     enrich
    0.30
    thr
    0.28
    once
    0.28
    chin
    0.27
    åĪ°æľĢåIJİ
    0.25
     once
    0.25
     enriched
    0.25
    ths
    0.24
     obs
    0.24
    otre
    0.24
    Activations Density 27.010%

    No Known Activations