© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 161711
    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
    riers
    -0.27
    éļľ
    -0.27
    .gms
    -0.26
     reim
    -0.25
    寨
    -0.25
    äºĭæķħåıijçĶŁ
    -0.25
    thritis
    -0.24
    workers
    -0.24
     DAMAGES
    -0.24
     Workers
    -0.24
    POSITIVE LOGITS
    ile
    0.26
    aml
    0.26
    ISK
    0.26
    tn
    0.25
    缮æłĩ
    0.25
    æĭ³å¤´
    0.25
    çĶŁçī©åѦ
    0.25
    æıĨ
    0.24
    ourcing
    0.24
    ten
    0.24
    Activations Density 0.070%

    No Known Activations

    This feature has no known activations.