© 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. 149649
    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
    bes
    -0.28
    ç»ĩ
    -0.26
    orus
    -0.26
    Facade
    -0.26
    atal
    -0.25
    俾
    -0.25
     hòa
    -0.25
     SETUP
    -0.24
    burg
    -0.24
    že
    -0.24
    POSITIVE LOGITS
    /down
    0.26
     thr
    0.24
     outr
    0.24
    Eight
    0.23
     defect
    0.23
    unan
    0.23
     averaging
    0.22
     designs
    0.22
     cop
    0.22
     coarse
    0.22
    Activations Density 0.332%

    No Known Activations

    This feature has no known activations.