© 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. 150192
    Prev
    Next
    INDEX
    Explanations

    -

    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
    èĥ½æĬĬ
    -0.26
     Bav
    -0.26
    paging
    -0.26
    çĺIJ
    -0.25
     conditioned
    -0.25
    еÑĢи
    -0.24
    ç¿ķ
    -0.24
    äºĨå¤ļå°ij
    -0.24
     postpon
    -0.23
     Germany
    -0.23
    POSITIVE LOGITS
    rosse
    0.27
    cola
    0.24
    arro
    0.24
    Intermediate
    0.24
    tra
    0.24
    ä¸ĢéŨ
    0.24
    TRA
    0.23
    ges
    0.23
    AdapterManager
    0.23
    gest
    0.23
    Activations Density 0.107%

    No Known Activations