© 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. 14-TRANSCODER-HP
    7. 39657
    Prev
    Next
    INDEX
    Explanations

    bones and joints

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    -SA
    -0.27
    åĹ£
    -0.26
    èĤīä½ĵ
    -0.26
    éĴ»çŁ³
    -0.24
    monds
    -0.24
     patched
    -0.24
     Palo
    -0.24
    .patch
    -0.24
     utility
    -0.23
    们éĥ½
    -0.23
    POSITIVE LOGITS
    ier
    0.33
    crow
    0.26
     Recorder
    0.26
    稳
    0.26
     Mis
    0.25
     Premiere
    0.25
    çĹ´
    0.25
     Cir
    0.24
    æľīåĵªäºĽ
    0.24
     Record
    0.24
    Activations Density 0.448%

    No Known Activations