INDEX

Explanations

sea

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¹²

-0.26

dry

-0.26

çĴł

-0.26

Arn

-0.25

 AssemblyCopyright

-0.25

 fray

-0.25

Erd

-0.25

/archive

-0.25

èįª

-0.24

 ç±

-0.24

POSITIVE LOGITS

 proximity

0.26

èĥĥåı£

0.25

èĦ±

0.25

åĬ£

0.25

RowIndex

0.24

nings

0.24

 xuá»ĳng

0.24

èİħ

0.24

Nec

0.24

æĦıæĦ¿

0.24

Activations Density 0.027%

sea

No Comments

No Known Activations