© 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. 53829
    Prev
    Next
    INDEX
    Explanations

    say "storage location" words

    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
    ë¡Ģ
    -0.28
    .asc
    -0.26
     AD
    -0.26
    inters
    -0.26
     ad
    -0.25
    -task
    -0.25
     purs
    -0.24
    (Task
    -0.24
    ãĥ¬ãĥĵ
    -0.24
    chy
    -0.24
    POSITIVE LOGITS
    æĺ¯ä¸Ģ座
    0.30
    ussy
    0.28
    boot
    0.26
    ág
    0.26
    亿åħĥ以ä¸Ĭ
    0.25
    egan
    0.25
    大çīĩ
    0.24
    æŀķ
    0.24
     boot
    0.23
    è¤Ĥ
    0.23
    Activations Density 0.005%

    No Known Activations