© 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. 95814
    Prev
    Next
    INDEX
    Explanations

    Military or research related texts

    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
    åĪ°æĿ¥
    -0.34
    åįĪ
    -0.29
    çģµéŃĤ
    -0.27
    缣
    -0.27
     Arrival
    -0.26
    次ä¼ļè®®
    -0.26
    æĿ¥ä¸´
    -0.26
     boss
    -0.26
    æľ¬æĬ¥
    -0.26
    Refresh
    -0.26
    POSITIVE LOGITS
    iners
    0.33
     wrappers
    0.31
    ces
    0.30
    tes
    0.29
    conti
    0.28
    ines
    0.28
    ules
    0.27
    scription
    0.27
    sel
    0.26
    INES
    0.26
    Activations Density 0.006%

    No Known Activations