© 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. 141284
    Prev
    Next
    INDEX
    Explanations

    proper nouns and descriptions

    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
    åķĨçĶ¨
    -0.28
    éĩįé»ŀ
    -0.26
     lag
    -0.26
    çĶŁäº§è®¾å¤ĩ
    -0.25
    opal
    -0.25
    éĩįçĤ¹
    -0.25
    .son
    -0.25
     Merchant
    -0.24
     Examiner
    -0.24
    @(
    -0.24
    POSITIVE LOGITS
    è§ģ
    0.31
    ÐĿÐķ
    0.28
    Fed
    0.28
    rouw
    0.27
    ceb
    0.27
    liers
    0.26
    çħ§
    0.26
    ény
    0.26
    .boost
    0.25
    atta
    0.25
    Activations Density 18.673%

    No Known Activations