© 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. 162644
    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
     ours
    -0.27
    æĪij们çļĦ
    -0.27
    cond
    -0.26
    ä¸Ī
    -0.25
    åĨĻçļĦ
    -0.25
    æķħ
    -0.24
    »¿
    -0.24
    æī«çłģ
    -0.24
     RouteServiceProvider
    -0.24
     assoc
    -0.24
    POSITIVE LOGITS
    oola
    0.34
     Legisl
    0.30
    oretical
    0.29
     IonicModule
    0.27
     Mot
    0.25
    åħ¨éĿ¢æıIJåįĩ
    0.25
     physically
    0.24
     Bucc
    0.24
    sworth
    0.24
    FromClass
    0.23
    Activations Density 0.189%

    No Known Activations

    This feature has no known activations.