© 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. 24214
    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
    LM
    -0.25
    DL
    -0.25
    DP
    -0.24
    umba
    -0.23
    lez
    -0.23
    ATED
    -0.23
     afforded
    -0.23
    igh
    -0.23
    erval
    -0.23
    çģµæ´»
    -0.23
    POSITIVE LOGITS
    pector
    0.27
    ä»ĸæĺ¯ä¸Ģ个
    0.25
     versa
    0.25
    ctors
    0.25
     directives
    0.25
    åģĮ
    0.25
     Glow
    0.24
     possessing
    0.23
    çĿ£åĬŀ
    0.23
     Principal
    0.23
    Activations Density 0.032%

    No Known Activations

    This feature has no known activations.