© 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. 25-TRANSCODER-HP
    7. 109464
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    altern
    -0.30
    ymb
    -0.29
    CTSTR
    -0.26
    à¹Ģà¸ģร
    -0.25
    æį¢å±Ĭ
    -0.24
    éĢī
    -0.24
    Moder
    -0.23
    licit
    -0.23
    cred
    -0.23
    utra
    -0.23
    POSITIVE LOGITS
    pod
    0.25
    åĪĨåŃIJ
    0.25
    ales
    0.25
    er
    0.25
     arousal
    0.24
    arine
    0.24
    à¹īา
    0.24
    nt
    0.24
    âĹ»
    0.24
    eger
    0.23
    Activations Density 0.114%

    No Known Activations

    This feature has no known activations.