© 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. 12-TRANSCODER-HP
    7. 23519
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ´¾åĩº
    -0.31
     Immediately
    -0.28
    æī¹åĩĨ
    -0.26
    iber
    -0.25
    iences
    -0.25
     perfectly
    -0.25
     Tonight
    -0.25
    els
    -0.24
    ue
    -0.24
    uent
    -0.23
    POSITIVE LOGITS
     _$
    0.30
    éģĴ
    0.24
    åºij
    0.24
    å½°
    0.24
    å®ŀä¸ļ
    0.24
    çŃīåIJĦç§į
    0.24
    åįĹåĮĹ
    0.24
    åѤ
    0.24
     nominate
    0.23
    Vect
    0.23
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.