© 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. 20-TRANSCODER-HP
    7. 129789
    Prev
    Next
    INDEX
    Explanations

    So

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rud
    -0.27
    使人
    -0.27
    EXTERNAL
    -0.27
     minded
    -0.27
    ä¸įæĪIJ
    -0.26
    åħīæ³½
    -0.26
    --+
    -0.25
    bote
    -0.25
    +=
    -0.25
    unlikely
    -0.25
    POSITIVE LOGITS
    reach
    0.30
    oux
    0.28
    far
    0.26
    ħ§
    0.25
    dent
    0.25
    iate
    0.24
     UsersController
    0.24
    è´¯
    0.24
     far
    0.23
    ctr
    0.23
    Activations Density 49.871%

    No Known Activations