© 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. 53606
    Prev
    Next
    INDEX
    Explanations

    technical/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
    carry
    -0.27
    (para
    -0.27
    ä¼łå¯¼
    -0.26
     citation
    -0.26
    -vars
    -0.25
    æIJºå¸¦
    -0.25
    转åıij
    -0.25
    æŶæĬ¥
    -0.25
    orth
    -0.24
    @d
    -0.24
    POSITIVE LOGITS
     master
    0.29
    ÃŃas
    0.27
    iae
    0.27
    snap
    0.27
    iaux
    0.25
    etas
    0.25
    iona
    0.25
    .master
    0.25
    wt
    0.24
    çĥŃ
    0.24
    Activations Density 0.007%

    No Known Activations