© 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. 24095
    Prev
    Next
    INDEX
    Explanations

    Mixed narrative and system descriptions

    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
     именно
    -0.26
     able
    -0.25
    -fold
    -0.25
    _vue
    -0.24
    egov
    -0.24
    åĨľå®¶
    -0.24
     exact
    -0.24
    åµĮ
    -0.23
    fold
    -0.23
    Embed
    -0.23
    POSITIVE LOGITS
    rick
    0.30
    åľ¨ç½ij绾
    0.30
     desn
    0.29
    shall
    0.27
    æīĵåĩ»
    0.25
     breaker
    0.25
    rite
    0.25
    >::
    0.24
    roduced
    0.24
     SHALL
    0.24
    Activations Density 0.000%

    No Known Activations