© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 27-TRANSCODER-HP
    7. 58319
    Prev
    Next
    INDEX
    Explanations

    Responding to questions with "That's"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¶Ĭ好
    -0.27
    åĬłåĪĨ
    -0.26
    ctp
    -0.26
    ’)
    -0.26
    鹧
    -0.26
    @show
    -0.25
    [↵
    -0.25
    ç§Ģ
    -0.25
    rypton
    -0.24
    é«ĺæķĪçļĦ
    -0.24
    POSITIVE LOGITS
    atee
    0.27
    esco
    0.26
    æľĽçĿĢ
    0.26
     header
    0.25
    ataka
    0.24
    帻
    0.24
     cÅĵur
    0.24
    oten
    0.24
     cose
    0.24
    ä¸Ģ个éĹ®é¢ĺ
    0.24
    Activations Density 0.008%

    No Known Activations