© 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. 27-TRANSCODER-HP
    7. 58337
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fits
    -0.27
     Appears
    -0.26
    糧
    -0.26
    imator
    -0.25
    ube
    -0.25
     .↵↵↵↵
    -0.25
    Unnamed
    -0.24
     affiliate
    -0.24
    ibe
    -0.24
    èĩªæľī
    -0.24
    POSITIVE LOGITS
    å½¹
    0.29
    è¿Ń
    0.28
    hea
    0.26
     –
    0.26
    æĶ¶å®ĺ
    0.26
    èĹĵ
    0.25
    witch
    0.25
    esion
    0.24
    åı¬
    0.24
    ืà¸Ńà¸Ļ
    0.24
    Activations Density 0.010%

    No Known Activations

    This feature has no known activations.