© 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. 95331
    Prev
    Next
    INDEX
    Explanations

    code or technical documentation

    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
    社ä¼ļåĮĸ
    -0.28
    鬻
    -0.27
    cast
    -0.26
    idian
    -0.26
    åłħ
    -0.25
    åıĭæĥħ
    -0.25
    社ä¼ļæ²»çIJĨ
    -0.25
    ниÑĩ
    -0.24
    gest
    -0.24
    å¹²åĺĽ
    -0.24
    POSITIVE LOGITS
    ahn
    0.25
     avail
    0.24
     fasc
    0.24
    chas
    0.24
    tty
    0.24
    æĦı
    0.24
    æĥ°
    0.23
    æĺ¯éŁ©åĽ½
    0.23
     limiting
    0.23
    hoff
    0.23
    Activations Density 0.782%

    No Known Activations