© 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. 24256
    Prev
    Next
    INDEX
    Explanations

    namespace

    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
    æķĪ
    -0.28
    ideon
    -0.25
    eneric
    -0.25
     Bran
    -0.25
    ftp
    -0.24
    çĤ¹å¤´
    -0.24
    (PropertyName
    -0.24
     soda
    -0.24
    .Cond
    -0.24
     initials
    -0.23
    POSITIVE LOGITS
     McGr
    0.30
     Associ
    0.27
    èĽĨ
    0.26
    /*@
    0.26
    amm
    0.25
    å°Ħæīĭ
    0.25
    éŃĶçİĭ
    0.24
    ringe
    0.24
    åĪĬ
    0.24
    pos
    0.24
    Activations Density 0.052%

    No Known Activations