INDEX

Explanations

law

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

RN

-0.26

 blockers

-0.25

 Foster

-0.25

ÑĥÑī

-0.25

æĻºæħ§

-0.25

vit

-0.24

ResponseType

-0.24

indows

-0.24

 tester

-0.24

Boston

-0.24

POSITIVE LOGITS

æµĳèº«

0.27

afe

0.27

ppy

0.26

æĥħå½¢

0.26

yan

0.26

 primitive

0.26

ä¿ĿæĬ¤åĮº

0.26

æī°ä¹±

0.25

cl

0.25

fts

0.25

Activations Density 0.004%

law

No Comments

No Known Activations