© 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. 20-TRANSCODER-HP
    7. 63523
    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_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ£į
    -0.28
     fam
    -0.28
     cu
    -0.27
     CB
    -0.24
     means
    -0.24
    âĨij
    -0.24
    éĥ¨
    -0.24
    обоÑĢоÑĤ
    -0.23
    ery
    -0.23
    plate
    -0.23
    POSITIVE LOGITS
     reconcile
    0.27
    SSIP
    0.26
    -President
    0.25
     $($
    0.25
    cmds
    0.24
    alue
    0.24
    essa
    0.24
    vox
    0.24
    mPid
    0.24
    empo
    0.24
    Activations Density 14.645%

    No Known Activations