INDEX

Explanations

Far

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

éģĹçķĻ

-0.28

reflect

-0.27

 Unified

-0.25

è¸Ĭ

-0.25

 reflects

-0.24

 reflecting

-0.24

prd

-0.24

rfl

-0.24

 Reflect

-0.24

Reflect

-0.24

POSITIVE LOGITS

åŃ£

0.29

æĿľ

0.29

 Targets

0.28

erto

0.26

 Comp

0.26

arta

0.26

 season

0.26

æ¢³çĲĨ

0.25

 targets

0.24

 artist

0.24

Activations Density 0.001%

Far

No Comments

No Known Activations