© 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. 33-TRANSCODER-HP
    7. 53688
    Prev
    Next
    INDEX
    Explanations

    Technical documents context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĨķ
    -0.31
     MEDIA
    -0.28
    ekt
    -0.27
     wart
    -0.26
    çªĹå¤ĸ
    -0.26
    axon
    -0.26
    erna
    -0.25
    æĻ®éĢļè¯Ŀ
    -0.24
     seo
    -0.24
    踵
    -0.24
    POSITIVE LOGITS
     Bi
    0.35
    bi
    0.32
    ç»ĻåĪ«äºº
    0.31
    Malloc
    0.27
    Bi
    0.27
     Ci
    0.27
    edited
    0.27
     bi
    0.27
     Brad
    0.25
    ç¼ĸ
    0.25
    Activations Density 0.012%

    No Known Activations