© 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. 64049
    Prev
    Next
    INDEX
    Explanations

    Claims/Evidence/Statements

    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
    abouts
    -0.30
    acks
    -0.29
    acking
    -0.27
    (non
    -0.27
    Posting
    -0.26
    tram
    -0.25
    pret
    -0.25
    ERM
    -0.25
    客
    -0.25
     adjacency
    -0.24
    POSITIVE LOGITS
    roe
    0.31
    ÑĢÑı
    0.28
    .setHorizontalAlignment
    0.28
    æ¸ĶèĪ¹
    0.27
    stown
    0.26
    ãĥĬãĥ³
    0.25
    交æ±ĩ
    0.25
     Bers
    0.24
    åĪĨ级
    0.24
     Bord
    0.24
    Activations Density 14.780%

    No Known Activations