INDEX

Explanations

that

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

çĥ§çĥ¤

-0.27

ysi

-0.27

ual

-0.26

 Inline

-0.24

esan

-0.24

xCC

-0.24

#"

-0.24

inc

-0.23

ince

-0.23

apur

-0.23

POSITIVE LOGITS

iminary

0.26

ä»¶

0.26

 party

0.26

ä¸Ģä»½

0.25

 bergen

0.25

ypes

0.25

licant

0.25

 gene

0.24

Teh

0.24

-signed

0.24

Activations Density 0.002%

that

No Comments

No Known Activations