© 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. 39780
    Prev
    Next
    INDEX
    Explanations

    programming/technical computing

    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
    Not in Any Lists

    No Comments

    Negative Logits
    iar
    -0.28
    sez
    -0.27
    夺
    -0.26
    -cluster
    -0.26
    æįŁå¤±
    -0.25
    çł´æįŁ
    -0.25
     stag
    -0.25
    cluster
    -0.25
    Cluster
    -0.24
    è½½
    -0.24
    POSITIVE LOGITS
    ondon
    0.27
    veys
    0.26
    trinsic
    0.26
    adow
    0.26
    alcon
    0.25
    Unsigned
    0.25
    ackbar
    0.25
    çŁŃçŁŃ
    0.24
    ibus
    0.24
    º«
    0.24
    Activations Density 1.027%

    No Known Activations