© 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. 30-TRANSCODER-HP
    7. 95817
    Prev
    Next
    INDEX
    Explanations

    Code and legal text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    acers
    -0.26
    umpt
    -0.26
    ozo
    -0.26
    Together
    -0.26
    odos
    -0.25
     together
    -0.25
    ters
    -0.25
    æĪĹ
    -0.25
    achu
    -0.25
    aters
    -0.24
    POSITIVE LOGITS
     Clo
    0.31
    Clo
    0.29
    çĶ¨åĬĽ
    0.27
     Lip
    0.26
    anos
    0.26
    æ´Ĺè¡£
    0.26
    (CancellationToken
    0.25
    çĶŁæ´»çݯå¢ĥ
    0.25
    gunakan
    0.25
     tilt
    0.23
    Activations Density 0.108%

    No Known Activations