© 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. 30-TRANSCODER-HP
    7. 96436
    Prev
    Next
    INDEX
    Explanations

    diseases and vaccines

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    obile
    -0.28
     vile
    -0.27
     Bray
    -0.26
     Charity
    -0.26
    è°ı
    -0.25
    auty
    -0.25
    pred
    -0.25
    verbs
    -0.24
    è¨Ģè¡Į
    -0.24
    çĥŃ线
    -0.24
    POSITIVE LOGITS
     natural
    0.35
    èĩªçĦ¶
    0.34
    ç¡IJ
    0.30
     exposure
    0.27
    Visible
    0.27
    adero
    0.27
    ToLocal
    0.27
    atural
    0.26
    atorio
    0.26
    natural
    0.26
    Activations Density 0.108%

    No Known Activations