© 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. 19-TRANSCODER-HP
    7. 9286
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ursors
    -0.25
    tracked
    -0.25
    &q
    -0.25
    STITUTE
    -0.24
     ÐľÐ¾Ñģк
    -0.24
    senal
    -0.24
     tink
    -0.23
    è¡¿
    -0.23
    July
    -0.23
     конеÑĩно
    -0.23
    POSITIVE LOGITS
    åĻ¨å®ĺ
    0.31
     organ
    0.27
    CP
    0.26
    dl
    0.26
    CHO
    0.26
    å§ij
    0.24
    çī¹ç§į
    0.24
    inkel
    0.24
    orr
    0.24
    交éĻħ
    0.23
    Activations Density 0.086%

    No Known Activations

    This feature has no known activations.