INDEX

Explanations

news and recent developments

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

ter

-0.31

çŃīåĽłç´ł

-0.28

den

-0.28

RON

-0.27

ter

-0.26

ENCY

-0.26

Ø±ÙĨ

-0.26

éĥ¦

-0.25

æĶ¾åľ¨

-0.25

OP

-0.24

POSITIVE LOGITS

orts

0.27

èµŃ

0.26

spath

0.26

redient

0.25

ewidth

0.25

ä½łåºĶè¯¥

0.25

èĬĿ

0.24

anchors

0.24

ortho

0.24

AccessException

0.24

Activations Density 0.042%

news and recent developments

No Comments

No Known Activations