© 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. 53969
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    antz
    -0.28
     properly
    -0.26
    py
    -0.26
    otherwise
    -0.26
    proper
    -0.25
    çİĦ
    -0.25
    pers
    -0.25
    æĪ·
    -0.25
    ides
    -0.25
    eg
    -0.25
    POSITIVE LOGITS
    æıĴ
    0.28
    â½´
    0.28
    matchCondition
    0.27
    otron
    0.25
    ewis
    0.25
    以èī²
    0.25
    plug
    0.25
    orns
    0.24
    =>"
    0.24
    oogle
    0.24
    Activations Density 0.006%

    No Known Activations

    This feature has no known activations.