© 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. 30-TRANSCODER-HP
    7. 95228
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ’T
    -0.30
    åĪĨå±Ģ
    -0.27
    ayer
    -0.27
    çĵ¶
    -0.26
    å±Ģ
    -0.25
    ground
    -0.25
    ’a
    -0.24
    åħ¹
    -0.24
    pper
    -0.24
    è¡Ķ
    -0.24
    POSITIVE LOGITS
    onen
    0.29
     cohorts
    0.27
    Collections
    0.26
    ICS
    0.26
     Romance
    0.26
    _RCC
    0.26
    ricular
    0.25
    èĽ©
    0.25
     alphabetical
    0.24
    IFO
    0.24
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.