© 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. 53724
    Prev
    Next
    INDEX
    Explanations

    1

    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
     possibilities
    -0.34
    ilder
    -0.28
    icorn
    -0.25
    èĥį
    -0.25
    æĺİåªļ
    -0.24
     types
    -0.24
    _effects
    -0.24
     Poss
    -0.24
     possibility
    -0.24
    agini
    -0.24
    POSITIVE LOGITS
    4
    0.40
    7
    0.36
    0
    0.35
    6
    0.33
    8
    0.32
    9
    0.32
    2
    0.31
    3
    0.30
    5
    0.30
    bia
    0.28
    Activations Density 0.012%

    No Known Activations