© 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. 304
    Prev
    Next
    INDEX
    Explanations

    Tolls

    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
    Hat
    -0.27
    hattan
    -0.26
    ivirus
    -0.26
    ;top
    -0.24
     Sed
    -0.23
    ced
    -0.23
    ROLE
    -0.23
    /Layout
    -0.23
    terior
    -0.23
    å¼Ĭ端
    -0.23
    POSITIVE LOGITS
     reflect
    0.29
    çłĶ究æīĢ
    0.26
    缴
    0.25
     Uni
    0.25
    ness
    0.25
    \Unit
    0.25
     favour
    0.25
    çŃīåĨħ容
    0.24
    缴è§Ĥ
    0.24
    åĩĨ
    0.24
    Activations Density 0.020%

    No Known Activations