© 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. 31-TRANSCODER-HP
    7. 19742
    Prev
    Next
    INDEX
    Explanations

    mark

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_31.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.31.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     bullet
    -0.29
    pty
    -0.27
     burdens
    -0.27
    é¢ł
    -0.27
     party
    -0.27
     binary
    -0.26
    binary
    -0.26
    gency
    -0.26
     brow
    -0.26
    ILED
    -0.25
    POSITIVE LOGITS
    oba
    0.29
    edd
    0.29
    çľĭåĪ°äºĨ
    0.26
     Seen
    0.25
    æªĶ
    0.25
    zsche
    0.24
    åı¯è§ģ
    0.24
    ssql
    0.24
    esub
    0.24
    ala
    0.24
    Activations Density 0.022%

    No Known Activations