© 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. 23-TRANSCODER-HP
    7. 24406
    Prev
    Next
    INDEX
    Explanations

    Numbers and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    为客æĪ·
    -0.30
    å°ĸ
    -0.28
    ény
    -0.26
    没æĥ³åĪ°
    -0.25
     tipped
    -0.25
     nostr
    -0.25
    enaire
    -0.24
     vapor
    -0.24
    .DataTable
    -0.24
     recept
    -0.24
    POSITIVE LOGITS
    Pub
    0.25
    件äºĭ
    0.25
    :")
    0.25
    »,
    0.24
    alia
    0.24
    å°±å¤Ł
    0.24
    åįģæĿ¡
    0.23
    ulp
    0.23
    robe
    0.22
     Origins
    0.22
    Activations Density 0.001%

    No Known Activations