© 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. 40826
    Prev
    Next
    INDEX
    Explanations

    excav

    np_max-act-logits · gemini-2.0-flash
    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
    Negative Logits
    ackets
    -0.32
    scopes
    -0.28
    PFN
    -0.28
    	cc
    -0.27
    ices
    -0.27
    ouched
    -0.27
    Sm
    -0.27
    imes
    -0.27
    odos
    -0.26
    (cc
    -0.26
    POSITIVE LOGITS
    plant
    0.33
     plant
    0.29
    ating
    0.28
    æ¤įçī©
    0.28
     Plant
    0.28
     touring
    0.27
     Poll
    0.25
    íĮħ
    0.25
    BorderStyle
    0.25
    аÑĤелÑĮ
    0.25
    Activations Density 0.001%

    No Known Activations