© 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. 53117
    Prev
    Next
    INDEX
    Explanations

    biological research texts

    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
    çĸ¾çĹħ
    -0.28
    riculum
    -0.28
    åĢ¾
    -0.28
    模åħ·
    -0.27
     ÑĤÑĢав
    -0.26
    æį·
    -0.26
    row
    -0.25
    æ¯įæł¡
    -0.25
    xx
    -0.25
    ä¸ĸ家
    -0.25
    POSITIVE LOGITS
     INTERNAL
    0.26
    pone
    0.26
    udit
    0.25
    æĵĺ
    0.25
    çİ°éĩij
    0.24
    UNCT
    0.24
    aniu
    0.24
    产åѦ
    0.23
    èĭįçĻ½
    0.23
     Sa
    0.23
    Activations Density 0.037%

    No Known Activations