© 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. 53608
    Prev
    Next
    INDEX
    Explanations

    cancer

    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
    .glide
    -0.27
    uli
    -0.26
    åĶ®
    -0.26
    cbd
    -0.26
    ckt
    -0.25
    pie
    -0.25
    ToF
    -0.25
     l
    -0.24
    work
    -0.24
    .AutoComplete
    -0.24
    POSITIVE LOGITS
    çģ¶
    0.29
    侬
    0.28
     reap
    0.26
    åį¿
    0.26
     surrounded
    0.24
     contr
    0.24
    é¢ijçİĩ
    0.24
    uÅŁ
    0.24
    -separated
    0.23
    æµĵ度
    0.23
    Activations Density 0.011%

    No Known Activations