© 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. 63205
    Prev
    Next
    INDEX
    Explanations

    an

    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
    åı¯èĥ½æĢ§
    -0.29
    -wise
    -0.28
    ãģĵ
    -0.26
    Aws
    -0.26
    inent
    -0.26
     wise
    -0.26
    äºĭæķħåıijçĶŁ
    -0.26
     verge
    -0.25
    åŀĵ
    -0.25
    .cfg
    -0.24
    POSITIVE LOGITS
    çļĦ人çī©
    0.30
    ales
    0.28
    ones
    0.24
    åĶ®
    0.23
    qid
    0.23
    ampa
    0.23
     depart
    0.23
    éĢłåŀĭ
    0.23
    ìĹŃ
    0.22
    onacci
    0.22
    Activations Density 19.212%

    No Known Activations