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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 163242
    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
    è¦ģåĬłå¼º
    -0.31
     conv
    -0.29
    æĽ´æĺ¯
    -0.28
    ç§ĥ
    -0.27
     sw
    -0.27
     mean
    -0.27
    conv
    -0.26
     use
    -0.26
    åĮĸèĤ¥
    -0.26
     used
    -0.26
    POSITIVE LOGITS
     afterward
    0.27
     поÑĤом
    0.27
    eking
    0.27
     grues
    0.26
    çĸ¼çĹĽ
    0.26
    tera
    0.26
     orchest
    0.26
     unlocking
    0.26
     someday
    0.25
     autopsy
    0.25
    Activations Density 0.027%

    No Known Activations

    This feature has no known activations.