© 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. 25-TRANSCODER-HP
    7. 107762
    Prev
    Next
    INDEX
    Explanations

    with

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æ´Ĺ
    -0.25
     KN
    -0.24
    hardt
    -0.24
     collaps
    -0.23
     para
    -0.23
     $$$
    -0.23
     Para
    -0.23
    ä¸ŃåIJ«æľī
    -0.23
    duc
    -0.22
    åĪĹ
    -0.22
    POSITIVE LOGITS
     its
    0.69
    åħ¶
    0.66
    its
    0.64
    Its
    0.59
     Its
    0.58
    å®ĥçļĦ
    0.56
    åħ¶æīĢ
    0.52
     their
    0.45
    their
    0.43
     его
    0.43
    Activations Density 0.917%

    No Known Activations