© 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. 24-TRANSCODER-HP
    7. 150696
    Prev
    Next
    INDEX
    Explanations

    Words starting with "d"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cluded
    -0.25
    alted
    -0.25
    обÑĢаз
    -0.24
    èĮ¸
    -0.24
    å½ĵåľº
    -0.24
    voke
    -0.23
    ãĤº
    -0.23
    åľĥ
    -0.23
     apex
    -0.23
    mez
    -0.23
    POSITIVE LOGITS
    igital
    0.48
    irectional
    0.43
    isplay
    0.41
    ragon
    0.40
    etermined
    0.40
    rive
    0.40
    esign
    0.40
    igits
    0.39
    ifferent
    0.38
    imensional
    0.37
    Activations Density 3.600%

    No Known Activations