© 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. 42893
    Prev
    Next
    INDEX
    Explanations

    people's names

    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
    æļĹ
    -0.31
    orf
    -0.28
     tilted
    -0.28
    rna
    -0.27
    éĴ¢
    -0.26
    åĪ¹
    -0.26
     unt
    -0.26
    moid
    -0.26
    iti
    -0.26
    ront
    -0.26
    POSITIVE LOGITS
     dagger
    0.26
    ael
    0.25
    Ãłng
    0.24
    pest
    0.24
     dep
    0.24
     unavoid
    0.23
     fic
    0.23
    å¾Ħ
    0.23
    _slow
    0.23
    (dep
    0.23
    Activations Density 0.002%

    No Known Activations