© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 14-TRANSCODER-HP
    7. 40894
    Prev
    Next
    INDEX
    Explanations

    cretion

    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
     cof
    -0.25
    cy
    -0.24
    plat
    -0.24
    mse
    -0.23
    åī¥
    -0.23
    flex
    -0.23
    Jerry
    -0.23
    iquid
    -0.23
     domains
    -0.23
    Jo
    -0.22
    POSITIVE LOGITS
    æĻ¯
    0.32
    aine
    0.31
    åīįçŀ»æĢ§
    0.29
     volley
    0.26
    .getStatus
    0.26
    antage
    0.25
    åħ¥åľº
    0.25
    两åıª
    0.24
    åĩĢ
    0.24
    /pm
    0.24
    Activations Density 0.267%

    No Known Activations