© 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. 24-TRANSCODER-HP
    7. 150546
    Prev
    Next
    INDEX
    Explanations

    research and data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    vens
    -0.31
    è¡£çī©
    -0.30
    äººåľ¨
    -0.28
    éĥ¨åĪĨåĨħ容
    -0.27
    visibility
    -0.26
    amy
    -0.26
    çļĦ人çī©
    -0.26
    å®īåħ¨æĦŁ
    -0.26
    éĥ¨åĪĨåľ°åĮº
    -0.26
    AMY
    -0.25
    POSITIVE LOGITS
     normally
    0.25
     Crud
    0.25
    beh
    0.23
    è¡
    0.23
     EditorGUI
    0.23
     equally
    0.23
    ç§Łè½¦
    0.23
    åħ®
    0.23
    nable
    0.23
     lease
    0.23
    Activations Density 1.191%

    No Known Activations