© 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. 12-TRANSCODER-HP
    7. 22316
    Prev
    Next
    INDEX
    Explanations

    city names

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĢłè¡Ģ
    -0.30
    utt
    -0.28
     portals
    -0.25
    errar
    -0.25
    è´Łè´£
    -0.25
    ogen
    -0.25
     import
    -0.24
    .addRow
    -0.24
    rou
    -0.24
    ash
    -0.24
    POSITIVE LOGITS
    æĪIJåĬŁçļĦ
    0.29
    å½ĵæŶçļĦ
    0.28
    teenth
    0.28
     GIVEN
    0.27
     initWith
    0.26
    å¤ĩ
    0.26
    æĹħéĢĶ
    0.26
    hma
    0.26
    bove
    0.25
     Whites
    0.25
    Activations Density 0.001%

    No Known Activations