© 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. 54265
    Prev
    Next
    INDEX
    Explanations

    medical text

    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
    je
    -0.29
    onne
    -0.27
    _SF
    -0.26
     representations
    -0.26
    ha
    -0.26
     representation
    -0.26
    骢
    -0.26
    ara
    -0.25
     che
    -0.25
    æ°ĶåĢĻ
    -0.24
    POSITIVE LOGITS
    allah
    0.28
    kir
    0.28
    åĽ«
    0.24
    roots
    0.24
    Ñģлож
    0.24
    -insert
    0.24
    ongyang
    0.24
    (insert
    0.24
     Insert
    0.23
     tongues
    0.23
    Activations Density 0.005%

    No Known Activations