© 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. 24-TRANSCODER-HP
    7. 150465
    Prev
    Next
    INDEX
    Explanations

    technical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Seasons
    -0.30
    iol
    -0.28
     Bracket
    -0.28
    olist
    -0.27
    /LICENSE
    -0.26
    æľīèī²
    -0.26
     lòng
    -0.26
    åħ³éŨ
    -0.26
     cre
    -0.25
    Angles
    -0.25
    POSITIVE LOGITS
     technical
    0.34
     research
    0.32
     training
    0.32
    æĬĢæľ¯äººåijĺ
    0.31
    人æīįéĺŁä¼į
    0.31
     technician
    0.30
     personnel
    0.30
    æĬĢæľ¯çłĶåıij
    0.30
    æĬĢæľ¯åĴĮ
    0.29
    technical
    0.29
    Activations Density 0.960%

    No Known Activations