© 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. 53975
    Prev
    Next
    INDEX
    Explanations

    gland

    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
     thing
    -0.27
    æĶ¯æĮģåĬĽåº¦
    -0.26
    æ¹Ķ
    -0.24
     Remix
    -0.24
    宵
    -0.24
    æĹĹå¸ľ
    -0.24
     afternoon
    -0.24
    å±ıèĶ½
    -0.24
     cheaper
    -0.24
    å¹²åĩĢ
    -0.24
    POSITIVE LOGITS
     present
    0.40
    _present
    0.34
    present
    0.32
    -present
    0.31
     Present
    0.30
    Present
    0.29
    uliar
    0.28
    ular
    0.28
    ulent
    0.28
    \\\\
    0.27
    Activations Density 0.029%

    No Known Activations