© 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. 42550
    Prev
    Next
    INDEX
    Explanations

    -

    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
    :`~
    -0.31
    ~-
    -0.28
    oi
    -0.27
    ~=
    -0.27
    Highlighted
    -0.26
    highlight
    -0.26
    uetype
    -0.25
    rella
    -0.25
    ersistent
    -0.25
    optional
    -0.25
    POSITIVE LOGITS
     -
    0.30
    æĬ
    0.27
     tit
    0.26
     tud
    0.26
    	Copyright
    0.25
    [âĢ¦]
    0.25
    ĪæĿĥ
    0.25
    arms
    0.25
     charge
    0.25
    æłĩçŃ¾
    0.24
    Activations Density 0.012%

    No Known Activations