© 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. 149549
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions

    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
     κ
    -0.27
    çŀĦåĩĨ
    -0.25
    |%
    -0.25
    ório
    -0.25
    ihn
    -0.25
    ¬ģ
    -0.24
    ...</
    -0.24
    xef
    -0.24
    åľ£è¯ŀ
    -0.24
    |\
    -0.24
    POSITIVE LOGITS
    mod
    0.27
     mates
    0.27
    obe
    0.26
    flows
    0.26
     mate
    0.26
    TLS
    0.25
    Mod
    0.25
    flow
    0.25
    entials
    0.25
    è²¼
    0.24
    Activations Density 0.199%

    No Known Activations