© 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. 297
    Prev
    Next
    INDEX
    Explanations

    drag

    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
    rhs
    -0.29
    çĶ²çĬ¶èħº
    -0.25
    _decor
    -0.23
    عد
    -0.23
    .jump
    -0.23
    alım
    -0.23
    aux
    -0.23
    ÑĢег
    -0.23
    ships
    -0.23
    dre
    -0.23
    POSITIVE LOGITS
     inherit
    0.30
     inherited
    0.28
     inheritance
    0.26
     Silence
    0.26
    quel
    0.25
     references
    0.25
    éĢīåĩº
    0.24
     Generic
    0.24
    ellan
    0.24
     Gentle
    0.24
    Activations Density 0.209%

    No Known Activations