INDEX

Explanations

research papers/articles

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

oline

-0.31

Branch

-0.28

 Branch

-0.27

è£ľ

-0.27

East

-0.26

 branch

-0.26

 Apost

-0.25

èĩ¨

-0.25

 Intermediate

-0.25

TH

-0.24

POSITIVE LOGITS

èĬ³

0.28

elo

0.28

GRES

0.27

æĪĳè¿ĺæĺ¯

0.27

amientos

0.26

ä¸ºèĩªå·±

0.26

èĩªå·±

0.25

æĶ¾

0.25

çļĦè®¾è®¡

0.25

ije

0.25

Activations Density 0.001%

research papers/articles

No Comments

No Known Activations