© 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. 149758
    Prev
    Next
    INDEX
    Explanations

    quarter

    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
    SystemService
    -0.30
    ConnectionFactory
    -0.26
    inherit
    -0.25
    justify
    -0.25
    system
    -0.25
    eral
    -0.25
     barg
    -0.24
    aber
    -0.24
    å¤Ħç½®
    -0.24
    wald
    -0.23
    POSITIVE LOGITS
    FR
    0.27
    å²Ĺ
    0.27
     FR
    0.27
    -parts
    0.26
    çªģçł´åı£
    0.25
    ç¥ľ
    0.24
    .FR
    0.24
    fr
    0.24
    éĤ£äºĽ
    0.24
    -notes
    0.24
    Activations Density 0.409%

    No Known Activations