© 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. 24-TRANSCODER-HP
    7. 149633
    Prev
    Next
    INDEX
    Explanations

    language descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    кон
    -0.27
    street
    -0.26
    åľ°
    -0.26
    TECTION
    -0.25
    (period
    -0.25
    eton
    -0.24
    TestCase
    -0.24
    hetto
    -0.24
    nas
    -0.24
     åľ
    -0.24
    POSITIVE LOGITS
     Linear
    0.29
     linear
    0.28
     lineno
    0.28
    eneg
    0.28
    -linear
    0.26
    linear
    0.26
     egal
    0.26
    æł¸åĩĨ
    0.26
    ignum
    0.26
    Linear
    0.26
    Activations Density 1.028%

    No Known Activations