INDEX

Explanations

French language

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

owa

-0.28

Sortable

-0.25

èįĲ

-0.25

lord

-0.24

ÙĦÙħ

-0.24

ä½ĨçĶ±äºİ

-0.24

 bard

-0.24

Ð¸ÐºÐ¸

-0.24

QUI

-0.24

ARK

-0.23

POSITIVE LOGITS

_DP

0.28

gain

0.27

 gains

0.27

subtype

0.26

getAttribute

0.25

å¹´ä¸ĭåįĬå¹´

0.25

 Specialists

0.25

ä¸įè§£

0.24

ãģ«ãģ¨ãģ£ãģ¦

0.24

á¸ŀ

0.24

Activations Density 0.004%

French language

No Comments

No Known Activations