INDEX

Explanations

Arch

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ä¾¿ä¼ļ

-0.28

 getUsername

-0.27

erator

-0.26

 pairwise

-0.26

çĶŃ

-0.26

 cree

-0.25

è¾ĵ

-0.25

cre

-0.24

åĪ«è¯´

-0.24

çīĽ

-0.24

POSITIVE LOGITS

å°ļ

0.27

çľ¼æ³ª

0.26

Raised

0.26

zab

0.26

ARGV

0.26

.rstrip

0.24

.styles

0.24

 ÑģÐ¿ÑĢÐ°Ð²

0.24

iov

0.24

æľĽ

0.24

Activations Density 0.005%

Arch

No Comments

No Known Activations