INDEX

Explanations

garden

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

 backtrack

-0.29

ennen

-0.28

istros

-0.27

tees

-0.26

backs

-0.25

quez

-0.24

 Leisure

-0.24

 NYPD

-0.24

 Authorities

-0.24

unar

-0.23

POSITIVE LOGITS

łéĻ¤

0.28

èĶĹ

0.26

urv

0.25

_UNS

0.25

éķı

0.25

itter

0.25

’acc

0.24

ander

0.24

mal

0.24

å¹´å¼Ģå§ĭ

0.24

Activations Density 0.000%

garden

No Comments

No Known Activations