© 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. 96143
    Prev
    Next
    INDEX
    Explanations

    French context

    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
     Flem
    -0.32
    mont
    -0.28
     Watt
    -0.26
    ¶Ī
    -0.26
    Spanish
    -0.25
     colon
    -0.25
    åĵļ
    -0.25
    æľīçĶ¨çļĦ
    -0.24
    æ°¸
    -0.24
    -FIRST
    -0.24
    POSITIVE LOGITS
    ever
    0.35
    èĬ
    0.28
     Paran
    0.27
    CHA
    0.27
    æĺ¯æĪijåĽ½
    0.26
    EOS
    0.26
     Augustine
    0.25
     Shield
    0.25
    chas
    0.25
    èģļåIJĪ
    0.24
    Activations Density 0.885%

    No Known Activations