© 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. 142078
    Prev
    Next
    INDEX
    Explanations

    advantages and disadvantages

    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
    umat
    -0.29
    friend
    -0.28
    basis
    -0.27
    ucs
    -0.26
     LOOP
    -0.25
    /mat
    -0.25
    union
    -0.24
     encouragement
    -0.24
    è¾į
    -0.24
    Foot
    -0.24
    POSITIVE LOGITS
     warranted
    0.29
    ãģ¶ãĤĬ
    0.27
    rocess
    0.25
    èĬ¸
    0.24
     full
    0.24
    иÑĪÑĮ
    0.24
    APSHOT
    0.24
    orgia
    0.24
    etyl
    0.24
    ÅĤo
    0.24
    Activations Density 5.629%

    No Known Activations