© 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. 24-TRANSCODER-HP
    7. 149564
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    aisy
    -0.28
     acesso
    -0.27
    澧
    -0.26
    ãĥĭãĥ¥
    -0.25
    磫
    -0.24
    á»±c
    -0.24
    ppe
    -0.24
    ç»ĵå®ŀ
    -0.24
    缴æݥ影åĵį
    -0.24
     Persian
    -0.24
    POSITIVE LOGITS
    ember
    0.26
    åĨħç§ij
    0.25
    ulk
    0.24
    SELL
    0.24
    ooth
    0.24
    åıijæĸĩ
    0.24
    åħ³æ³¨åº¦
    0.24
     tut
    0.24
    UNC
    0.24
    (MediaType
    0.24
    Activations Density 0.186%

    No Known Activations

    This feature has no known activations.