INDEX

Explanations

varied text snippets/excerpts

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

iqu

-0.28

å½

-0.27

çĶ³

-0.27

çīĪ

-0.26

 McCarthy

-0.26

 remotely

-0.25

 Moder

-0.25

ë¦ĩ

-0.25

çłĶè®¨ä¼ļ

-0.25

çĽĳ

-0.24

POSITIVE LOGITS

éħĴç²¾

0.28

 enjo

0.27

éĽĨä¸Ńåľ¨

0.27

inges

0.25

cst

0.25

 dispers

0.25

.getLine

0.24

ertools

0.24

uing

0.24

 footwear

0.24

Activations Density 0.011%

varied text snippets/excerpts

No Comments

No Known Activations