© 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. 4-TRANSCODER-HP
    7. 251
    Prev
    Next
    INDEX
    Explanations

    c

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    éĤ£éĩĮ
    -0.28
     Proud
    -0.27
    osto
    -0.27
    prs
    -0.27
     Roths
    -0.26
    å§Ĭ妹
    -0.25
    rij
    -0.25
    hte
    -0.25
    stands
    -0.25
    /AP
    -0.25
    POSITIVE LOGITS
    ello
    0.26
     Scaffold
    0.26
    gó
    0.25
    purpose
    0.24
     sn
    0.24
    dismiss
    0.24
    ç»ĨåĪĻ
    0.24
    åĪĨæŀIJ
    0.23
     sk
    0.23
    wrapper
    0.23
    Activations Density 0.008%

    No Known Activations