© 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. 53518
    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
    oud
    -0.35
    inks
    -0.28
    uth
    -0.27
    ooth
    -0.26
    夹
    -0.26
    æ¿ĢçĥĪ
    -0.25
    ibo
    -0.25
    inking
    -0.25
    few
    -0.24
     Eid
    -0.24
    POSITIVE LOGITS
    -sales
    0.29
    ä¿Ħä¹Į
    0.27
    -watch
    0.26
    erus
    0.25
    WI
    0.25
    _PG
    0.25
    -caption
    0.25
    åģļ好
    0.24
    -store
    0.23
    @stop
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.