© 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. 52806
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    Not in Any Lists

    No Comments

    Negative Logits
    stones
    -0.30
    å²±
    -0.25
     пÑĢинима
    -0.25
    -independent
    -0.24
    soon
    -0.24
    iele
    -0.24
    oids
    -0.24
     Holocaust
    -0.24
    -changing
    -0.23
    ieve
    -0.23
    POSITIVE LOGITS
    缴
    0.28
     straight
    0.26
    onis
    0.26
    heit
    0.25
    常è§Ħ
    0.24
     back
    0.24
    åıijè¨Ģ
    0.24
    缴æµģ
    0.23
     Back
    0.23
    央
    0.23
    Activations Density 0.001%

    No Known Activations

    This feature has no known activations.