INDEX

Explanations

years

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

usan

-0.32

å¯¹å¾ħ

-0.29

è£Ļ

-0.29

uale

-0.28

æıĲåĪ°

-0.27

ä¹³æĪ¿

-0.27

idad

-0.26

æľĪç»ı

-0.26

çŀª

-0.25

æıĲåıĬ

-0.25

POSITIVE LOGITS

 Kushner

0.30

stile

0.27

 unknown

0.25

 rushed

0.25

 labels

0.25

Ã©rc

0.24

rec

0.24

htags

0.24

ABL

0.24

imest

0.23

Activations Density 0.004%

years

No Comments

No Known Activations