© 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. 54334
    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
     Hyper
    -0.29
    getParam
    -0.26
    ao
    -0.26
    Hyper
    -0.26
    aux
    -0.25
    airs
    -0.25
    _TEM
    -0.25
    PropertyValue
    -0.24
    campaign
    -0.24
     hyper
    -0.24
    POSITIVE LOGITS
    ique
    0.28
    cket
    0.27
    cratch
    0.26
     poor
    0.24
    iquement
    0.24
    ç¼ĺ
    0.24
    çĻ¾ä½Ļ
    0.23
    æĮŁ
    0.23
    plit
    0.23
     lent
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.