© 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. 41999
    Prev
    Next
    INDEX
    Explanations

    technical writing

    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
    èĤĮèĤī
    -0.32
    alan
    -0.30
    cly
    -0.29
    鼷
    -0.25
    aland
    -0.25
    裴
    -0.24
    IED
    -0.24
    istor
    -0.24
    çĶŁæ¶¯
    -0.24
     muscular
    -0.24
    POSITIVE LOGITS
    utable
    0.30
    (:,:,
    0.28
    SURE
    0.26
    mdb
    0.26
     Released
    0.26
    ger
    0.26
     cob
    0.24
    åĨł
    0.24
     har
    0.24
     coron
    0.24
    Activations Density 0.000%

    No Known Activations