INDEX

Explanations

Why

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å¤©æīį

-0.30

**

-0.27

emen

-0.27

]**

-0.26

è¿ľ

-0.26

 Goodman

-0.25

æ¥£

-0.25

Ð½Ð´ÐµÐºÑģ

-0.25

 trend

-0.24

èģĶ

-0.24

POSITIVE LOGITS

æľīæīĢ

0.29

ismet

0.28

kit

0.28

DTV

0.28

 cris

0.25

es

0.24

&lt

0.24

aaS

0.24

yar

0.24

ascimento

0.24

Activations Density 0.009%

Why

No Comments

No Known Activations