© 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. 42655
    Prev
    Next
    INDEX
    Explanations

    Languages and code

    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
    ADDING
    -0.27
    è¿ĩ硬
    -0.25
     Hath
    -0.25
    çĶľ
    -0.25
     Yaz
    -0.24
    çĶľç¾İ
    -0.24
    æŃĮ
    -0.24
    -terrorism
    -0.23
    AVIS
    -0.23
    æĪĺèĥľ
    -0.23
    POSITIVE LOGITS
    IO
    0.30
    etch
    0.29
    Serializer
    0.28
    Labels
    0.28
    æĬ½
    0.28
    li
    0.26
    labels
    0.26
    ience
    0.26
    io
    0.26
     serial
    0.26
    Activations Density 0.000%

    No Known Activations