© 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. 22229
    Prev
    Next
    INDEX
    Explanations

    getting something from something

    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
    Not in Any Lists

    No Comments

    Negative Logits
    з
    -0.28
     support
    -0.26
     pap
    -0.25
    管
    -0.25
    éŃĶ鬼
    -0.25
    /repository
    -0.24
    cript
    -0.24
    support
    -0.24
    çĽ¯
    -0.24
     rentals
    -0.24
    POSITIVE LOGITS
    มวล
    0.30
    IZES
    0.28
    )obj
    0.25
    æĦ¿
    0.25
    æķķ
    0.25
    evenodd
    0.25
    /rem
    0.25
    åĽŀåIJĪ
    0.24
    赦
    0.24
    <Func
    0.24
    Activations Density 0.002%

    No Known Activations