INDEX

Explanations

bank names, legal 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

atee

-0.30

edReader

-0.28

 gutter

-0.27

çĺª

-0.27

urses

-0.26

edm

-0.25

çŃ¹å»º

-0.24

¹Ħ

-0.24

æĶ¹åĪ¶

-0.24

 Thin

-0.24

POSITIVE LOGITS

ä¾¿

0.31

zia

0.28

Tur

0.27

tur

0.27

åĬ¨

0.26

å§¿

0.26

 parad

0.26

ä½ı

0.26

tur

0.25

æŁı

0.25

Activations Density 0.004%

bank names, legal language

No Comments

No Known Activations