© 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. 32-TRANSCODER-HP
    7. 43961
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ham
    -0.28
    esi
    -0.27
    òng
    -0.27
     emb
    -0.26
    horn
    -0.26
    à¹Ģà¸ķ
    -0.26
    oru
    -0.26
    èѦ
    -0.25
    ami
    -0.25
    Hack
    -0.25
    POSITIVE LOGITS
    ]=>
    0.29
    kah
    0.27
    稽
    0.26
     typings
    0.26
    _literals
    0.26
    eor
    0.25
    ÐļÐIJ
    0.25
    >((
    0.25
    eph
    0.25
     ys
    0.24
    Activations Density 0.000%

    No Known Activations