© 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. 41432
    Prev
    Next
    INDEX
    Explanations

    American or British

    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
    def
    -0.30
     def
    -0.29
     (#
    -0.26
    æ¨Ĺ
    -0.25
    _def
    -0.25
    ëħ¹
    -0.25
    blink
    -0.24
    fare
    -0.24
    =\"#
    -0.24
    Defs
    -0.24
    POSITIVE LOGITS
    éĥ¨
    0.31
    交
    0.27
    mits
    0.25
     Coast
    0.25
    itt
    0.25
    çĽ¸ä¼ł
    0.25
     yapılacak
    0.24
    åħ½
    0.24
    atee
    0.24
    olute
    0.23
    Activations Density 0.001%

    No Known Activations