© 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. 129659
    Prev
    Next
    INDEX
    Explanations

    code, lists, special characters

    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
     lẫn
    -0.28
    or
    -0.27
    Detail
    -0.27
    æī¯
    -0.25
    olicy
    -0.24
    thing
    -0.24
    è°µ
    -0.24
    Details
    -0.24
    Java
    -0.24
    orca
    -0.23
    POSITIVE LOGITS
    ikh
    0.26
    éĺħ读
    0.25
    obia
    0.25
    führung
    0.25
    ACY
    0.25
    porte
    0.24
    ië
    0.24
    ä»ŀ
    0.24
    gregate
    0.24
    ABL
    0.23
    Activations Density 20.825%

    No Known Activations