INDEX

Explanations

physical objects/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

é¸·

-0.26

 pretending

-0.26

é¸³

-0.25

 eagerly

-0.24

ãĢħ

-0.24

orum

-0.24

"|"

-0.24

NYT

-0.24

çĽ¸å¹²

-0.24

çĸ£

-0.24

POSITIVE LOGITS

åģļä¸įåĪ°

0.26

 distributes

0.26

å¤§å®Ĺ

0.25

ework

0.25

 Dirk

0.25

imentary

0.24

amas

0.24

arnation

0.23

åħ¶ä»ĸçİ©å®¶

0.23

å®¹

0.23

Activations Density 0.002%

physical objects/locations

No Comments

No Known Activations