© 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. 149891
    Prev
    Next
    INDEX
    Explanations

    Proper nouns

    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
    iday
    -0.26
     bum
    -0.26
    eway
    -0.26
    dependent
    -0.25
     Chunk
    -0.25
     substantive
    -0.25
    face
    -0.25
    å£
    -0.24
    bucket
    -0.24
     chemistry
    -0.24
    POSITIVE LOGITS
    磫
    0.28
    ((*
    0.26
    haft
    0.24
    rün
    0.24
    aveled
    0.24
    ëĤŃ
    0.23
    antas
    0.23
    zee
    0.23
     Canary
    0.23
    zier
    0.23
    Activations Density 0.106%

    No Known Activations