© 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. 23-TRANSCODER-HP
    7. 23975
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    auté
    -0.27
     body
    -0.25
     vide
    -0.24
    goals
    -0.24
    ãĥĹ
    -0.24
     pool
    -0.23
    cro
    -0.23
    çĤĻ
    -0.23
    rai
    -0.23
     acquiring
    -0.23
    POSITIVE LOGITS
    etty
    0.26
    imbus
    0.24
    artner
    0.24
    agas
    0.23
     massa
    0.23
    Comparer
    0.22
     {}:
    0.22
    éĻ¢éĻ¢å£«
    0.22
     Enumeration
    0.22
    åĬ¨çĶŁæĪIJ
    0.22
    Activations Density 0.002%

    No Known Activations

    This feature has no known activations.