© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 57344
    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
    æĦĨ
    -0.29
    éļĻ
    -0.27
    imore
    -0.26
    angs
    -0.26
     declare
    -0.25
    ecret
    -0.25
    synthesize
    -0.24
    rors
    -0.24
     unloaded
    -0.24
    声æĺİ
    -0.24
    POSITIVE LOGITS
    æĹºåŃ£
    0.27
    iber
    0.25
    çĻ½é©¬
    0.25
    è¡Įäºĭ
    0.24
     sper
    0.24
    ä¸ĩ欧åħĥ
    0.24
    Gamma
    0.23
    ĵį
    0.23
    plex
    0.23
    abic
    0.23
    Activations Density 0.920%

    No Known Activations

    This feature has no known activations.