© 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. 12-TRANSCODER-HP
    7. 22032
    Prev
    Next
    INDEX
    Explanations

    sought/anticipated

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    人éĢī
    -0.26
    ä¸Ģ次
    -0.26
    anoi
    -0.25
    踢
    -0.25
    der
    -0.25
    _rat
    -0.25
     CWE
    -0.24
    »
    -0.24
    &&!
    -0.24
    ources
    -0.24
    POSITIVE LOGITS
     mor
    0.28
    åłĩ
    0.27
    rical
    0.26
    Dispose
    0.26
     inherits
    0.26
    çķħ
    0.26
    éĢĨ
    0.25
    ä¸įåģľåľ°
    0.25
    æ£Ģ
    0.25
     junk
    0.25
    Activations Density 0.004%

    No Known Activations