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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 32-TRANSCODER-HP
    7. 43030
    Prev
    Next
    INDEX
    Explanations

    conveyor and elevator

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    reta
    -0.28
    èģĶ
    -0.28
    маÑĤ
    -0.26
     Duty
    -0.25
    æłī
    -0.24
    enus
    -0.24
     Am
    -0.24
    ãĤ¢ãĤ¦
    -0.24
    aminer
    -0.24
     Cob
    -0.24
    POSITIVE LOGITS
    åı£æ°Ķ
    0.29
     reversal
    0.28
    ce
    0.28
    ider
    0.26
    ester
    0.25
    å®ļ
    0.25
     th
    0.25
     beer
    0.23
    loth
    0.23
     ball
    0.23
    Activations Density 0.001%

    No Known Activations