INDEX

Explanations

Locations

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

)?$

-0.27

æĲĤ

-0.27

æľįä»İ

-0.26

å¥³ç¥ŀ

-0.26

 seizing

-0.26

:///

-0.25

Ð¸Ð»Ð¾ÑģÑĮ

-0.25

_lo

-0.25

çīĿ

-0.25

uum

-0.25

POSITIVE LOGITS

åħ¬çĽĬæĢ§

0.33

jection

0.28

np

0.27

 Depths

0.26

 object

0.26

 stage

0.25

usa

0.25

çĪ¹

0.24

object

0.24

ble

0.24

Activations Density 0.002%

Locations

No Comments

No Known Activations