© 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. 20-TRANSCODER-HP
    7. 129905
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    pdb
    -0.28
    ør
    -0.26
     passwd
    -0.25
    èĨ¦
    -0.24
    tract
    -0.24
    _invoke
    -0.24
    游
    -0.23
    mouseup
    -0.23
    uki
    -0.23
    lector
    -0.23
    POSITIVE LOGITS
    çĹ£
    0.28
     tele
    0.24
     backstage
    0.23
     supplemented
    0.22
    TestCategory
    0.22
    bow
    0.22
    åħĪåIJİ
    0.22
    æĽ´é«ĺ
    0.22
    æĽ´å¤§
    0.22
    éĢĥ
    0.22
    Activations Density 40.144%

    No Known Activations

    This feature has no known activations.