© 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. 33-TRANSCODER-HP
    7. 53365
    Prev
    Next
    INDEX
    Explanations

    medical, scientific texts

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ió
    -0.29
    çĺ´
    -0.28
    产åĵģçłĶåıij
    -0.27
    uala
    -0.25
    ymmetric
    -0.25
     shave
    -0.25
    iteDatabase
    -0.25
     Bronze
    -0.25
    ippers
    -0.25
     PROCUREMENT
    -0.25
    POSITIVE LOGITS
    ots
    0.35
    ot
    0.32
    ats
    0.31
    OTS
    0.31
    als
    0.31
    onn
    0.31
    oine
    0.30
    adc
    0.27
    own
    0.27
    oot
    0.27
    Activations Density 0.135%

    No Known Activations