INDEX

Explanations

spor

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

æ¬

-0.27

tridge

-0.26

Tre

-0.26

.shtml

-0.24

pig

-0.24

Tre

-0.24

èµ°åľ¨

-0.24

pig

-0.24

okit

-0.24

fig

-0.24

POSITIVE LOGITS

 kosten

0.30

 weigh

0.28

çĹķ

0.28

 weighing

0.28

weigh

0.27

leet

0.27

 weighed

0.27

 renters

0.26

ynes

0.26

ikel

0.24

Activations Density 0.003%

spor

No Comments

No Known Activations