© 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. 33-TRANSCODER-HP
    7. 53686
    Prev
    Next
    INDEX
    Explanations

    mail

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æī³
    -0.28
    esthetic
    -0.26
    [maxn
    -0.25
    ä¹±
    -0.25
    ét
    -0.25
    à¹īà¸Ļ
    -0.24
     nursery
    -0.24
     {%
    -0.24
    omy
    -0.23
    æ¸ħ
    -0.23
    POSITIVE LOGITS
     mails
    0.38
     present
    0.37
     MAIL
    0.35
    mail
    0.31
     postcode
    0.30
     mail
    0.30
     postal
    0.30
    éĤ®
    0.30
     sign
    0.29
     bind
    0.29
    Activations Density 0.049%

    No Known Activations