INDEX

Explanations

steps and stages

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

åħ¬åħ±èµĦæºĲ

-0.29

_bb

-0.27

è½¦ä½į

-0.26

èĩªç§ģ

-0.25

uvw

-0.25

outh

-0.25

actor

-0.24

Ä±k

-0.24

Cow

-0.24

zu

-0.24

POSITIVE LOGITS

 Terraria

0.29

ä¸Ģè¶Ł

0.28

AGMA

0.27

 alice

0.26

memberOf

0.26

æŁ¥çľĭæĽ´å¤ļ

0.25

alice

0.25

 Returning

0.24

 terra

0.24

è¿İæĿ¥äºĨ

0.24

Activations Density 1.188%

steps and stages

No Comments

No Known Activations