© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52549
    Prev
    Next
    INDEX
    Explanations

    'H

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    å±Ģ
    -0.29
    osos
    -0.27
    ARP
    -0.27
    åºĬä½į
    -0.26
     Hil
    -0.26
    arp
    -0.25
    表åĨ³
    -0.25
    oses
    -0.24
    ocols
    -0.24
    çĶ³
    -0.24
    POSITIVE LOGITS
    åľ¨äºİ
    0.26
    çĥĻ
    0.25
     banker
    0.25
    AGER
    0.25
     wrestling
    0.25
    NDER
    0.25
    doors
    0.25
     Closure
    0.24
     lineman
    0.24
    BAT
    0.24
    Activations Density 0.003%

    No Known Activations