© 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. 53076
    Prev
    Next
    INDEX
    Explanations

    Cell biology contexts

    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
    illo
    -0.28
    illos
    -0.28
    bian
    -0.28
    对äºİæĪij们
    -0.26
    ercul
    -0.26
    åŀĵ
    -0.26
    itz
    -0.25
    itized
    -0.25
     pragma
    -0.24
    walker
    -0.24
    POSITIVE LOGITS
    é£İ鼨
    0.27
    assi
    0.27
    aped
    0.26
    åĩŃ
    0.25
     encoded
    0.24
    éĻ
    0.24
     CL
    0.24
    ãĤ¸ãĥ£ãĥ¼
    0.24
    -encoded
    0.24
    oons
    0.24
    Activations Density 0.010%

    No Known Activations