INDEX

Explanations

organizations

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

lst

-0.28

sf

-0.27

uento

-0.27

 mating

-0.25

present

-0.24

 Bush

-0.24

è®¤è¯ģ

-0.24

line

-0.24

 proven

-0.24

anche

-0.24

POSITIVE LOGITS

oki

0.28

rians

0.27

Lat

0.26

conditionally

0.24

 cleans

0.24

-strip

0.24

æ¼Ĥ

0.23

asionally

0.23

 Venez

0.23

Activations Density 0.001%

organizations

No Comments

No Known Activations