© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 4-TRANSCODER-HP
    7. 300
    Prev
    Next
    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_4.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.4.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    urai
    -0.30
    .inject
    -0.26
     regist
    -0.24
    cies
    -0.24
    .TryParse
    -0.23
     Portal
    -0.23
    è¿ģ
    -0.23
     Microsystems
    -0.23
    hek
    -0.23
    jective
    -0.23
    POSITIVE LOGITS
    amm
    0.29
    rik
    0.25
    æIJģ
    0.25
     purported
    0.25
    *g
    0.25
    -million
    0.25
     potentials
    0.25
    ert
    0.24
    TAB
    0.24
     supposedly
    0.24
    Activations Density 0.039%

    No Known Activations