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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 23-TRANSCODER-HP
    7. 162702
    Prev
    Next
    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    çĸĸ
    -0.26
    æľĢåıĹ欢è¿İ
    -0.25
    çĸ±
    -0.25
    phan
    -0.25
    section
    -0.25
    ogs
    -0.25
    å¾Īå¤ļæŶåĢĻ
    -0.24
    catalog
    -0.24
    owel
    -0.24
    头èĦij
    -0.23
    POSITIVE LOGITS
     circ
    0.27
     HAR
    0.26
    æ²»
    0.26
     raced
    0.26
    eacher
    0.25
    'es
    0.25
    posables
    0.25
    SEE
    0.25
     End
    0.24
    æ¢Ń
    0.24
    Activations Density 0.009%

    No Known Activations