© 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. 30-TRANSCODER-HP
    7. 96304
    Prev
    Next
    INDEX
    Explanations

    code with 20XX years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    .Err
    -0.26
    staff
    -0.25
     Vaughan
    -0.25
     staff
    -0.25
     valued
    -0.25
     czÄĻsto
    -0.24
    обÑĭ
    -0.24
    尤为éĩįè¦ģ
    -0.23
    éĸĥ
    -0.23
    è¿ĺä¸įå¦Ĥ
    -0.23
    POSITIVE LOGITS
    oca
    0.30
    uzzi
    0.26
    ixer
    0.26
    xing
    0.26
    itize
    0.26
    çıŃ
    0.25
    åıijçĶŁ
    0.25
     Shield
    0.25
    çĿĢ
    0.25
    çıŃ级
    0.24
    Activations Density 0.882%

    No Known Activations