© 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. 23-TRANSCODER-HP
    7. 161956
    Prev
    Next
    INDEX
    Explanations

    accomplishments and records

    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
    åįģ大
    -0.42
    åįģä½³
    -0.35
     thirteen
    -0.34
     ten
    -0.33
    ä¹Ŀ大
    -0.33
    äºĶ大
    -0.32
    çĻ¾å¼º
    -0.32
     fifty
    -0.31
     Ten
    -0.31
     fifteen
    -0.31
    POSITIVE LOGITS
    ismet
    0.29
    qm
    0.27
    clr
    0.26
    IFO
    0.26
    igon
    0.25
     feu
    0.25
     Sala
    0.24
     exclusively
    0.24
     étant
    0.24
    åħįè²»
    0.24
    Activations Density 0.004%

    No Known Activations