© 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. 161624
    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
    ÎĽ
    -0.28
    çĢĽ
    -0.26
     veg
    -0.26
    loon
    -0.26
    主æĮģ人
    -0.26
    =is
    -0.25
    主æĮģ
    -0.25
    PET
    -0.25
    edList
    -0.25
    çĦ¶å¾Į
    -0.25
    POSITIVE LOGITS
     javafx
    0.29
    仪表
    0.29
     counters
    0.25
     ACM
    0.25
    stå
    0.24
    incident
    0.24
    äºĭ
    0.23
     igen
    0.23
     hawk
    0.23
    pl
    0.23
    Activations Density 0.004%

    No Known Activations

    This feature has no known activations.