© 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. 39430
    Prev
    Next
    INDEX
    Explanations

    -

    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
     TODAY
    -0.30
    ä¿Ĺ
    -0.30
    Session
    -0.27
    ungs
    -0.27
    åĬ¨æijĩ
    -0.26
    una
    -0.26
    ìĦŃ
    -0.26
     replace
    -0.25
    å®īåįĵ
    -0.25
    phans
    -0.25
    POSITIVE LOGITS
    ctica
    0.28
    ampoline
    0.27
     newState
    0.26
    nis
    0.26
    /sn
    0.25
    luent
    0.24
    Buff
    0.24
    BUFF
    0.24
    æ²³
    0.23
    ancy
    0.23
    Activations Density 0.076%

    No Known Activations