© 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. 32-TRANSCODER-HP
    7. 41522
    Prev
    Next
    INDEX
    Explanations

    Code and titles

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mani
    -0.32
    åŃIJéĩĮ
    -0.27
    referrer
    -0.24
    THR
    -0.24
    à¸ģล
    -0.23
    alg
    -0.23
     REFER
    -0.23
     prevail
    -0.23
    _par
    -0.23
    åıĭ
    -0.23
    POSITIVE LOGITS
    ...
    0.29
    âĢ¦
    0.27
    åıłåĬł
    0.26
    -intensive
    0.25
    ges
    0.24
    æīĵåĩ»
    0.24
    hit
    0.24
     truyá»ģn
    0.24
    ignum
    0.23
    adden
    0.23
    Activations Density 0.000%

    No Known Activations