© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52600
    Prev
    Next
    INDEX
    Explanations

    various specific contexts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    abl
    -0.27
    ronics
    -0.26
     groom
    -0.26
    aber
    -0.25
    èģĶ
    -0.25
    -dismiss
    -0.25
     beta
    -0.25
    沿线
    -0.24
    less
    -0.24
    éĹ»
    -0.24
    POSITIVE LOGITS
    蹬
    0.25
    <location
    0.25
    servername
    0.25
     IonicModule
    0.24
    [ix
    0.24
     Fair
    0.24
    parsers
    0.24
    posição
    0.24
    Convention
    0.24
     Mid
    0.23
    Activations Density 0.007%

    No Known Activations