INDEX

Explanations

ATS

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

bel

-0.28

ragment

-0.25

è®©èĩªå·±

-0.25

ogy

-0.25

ipheral

-0.25

çĤ¹å¤ļ

-0.24

emain

-0.23

è®©ä»ĸä»¬

-0.23

åįĬå²Ľ

-0.23

rone

-0.23

POSITIVE LOGITS

Ori

0.28

èģĬèģĬ

0.26

åħ¥åľº

0.25

ortal

0.24

 downwards

0.24

è§Ħæł¼

0.24

steen

0.24

ãģ¯ãģĵãģ¡ãĤī

0.24

 addAction

0.23

utches

0.23

Activations Density 0.002%

ATS

No Comments

No Known Activations