© 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. 150606
    Prev
    Next
    INDEX
    Explanations

    deed

    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
     rep
    -0.27
     cohesion
    -0.27
     quo
    -0.26
    führer
    -0.25
     invol
    -0.25
    odal
    -0.25
     effort
    -0.24
     recognition
    -0.24
     presum
    -0.24
     synthesized
    -0.24
    POSITIVE LOGITS
    enny
    0.28
     Sant
    0.25
     santé
    0.24
    ATS
    0.24
     wides
    0.24
    ITS
    0.24
    ||
    0.24
    lique
    0.23
     springfox
    0.23
     FUCK
    0.23
    Activations Density 0.051%

    No Known Activations