© 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. 32-TRANSCODER-HP
    7. 42203
    Prev
    Next
    INDEX
    Explanations

    Technical documents and breastfeeding

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ham
    -0.30
    æ¡Ĩæŀ¶
    -0.29
     Ham
    -0.28
    ham
    -0.28
    BER
    -0.27
    crc
    -0.27
    åĵĪ
    -0.27
    ardu
    -0.27
    FRAME
    -0.26
    æĸ°å½¢åĬ¿ä¸ĭ
    -0.26
    POSITIVE LOGITS
    ecast
    0.26
    social
    0.26
    åѤçĭ¬
    0.26
     social
    0.25
    ä¸Ģéĥ¨
    0.25
     vet
    0.25
     feed
    0.24
    ä¸Ģè¾¹
    0.24
    èĻij
    0.24
    Ñĩи
    0.24
    Activations Density 0.001%

    No Known Activations