INDEX

Explanations

Measurements

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 mind

-0.28

 agents

-0.28

atables

-0.27

èŃĺ

-0.26

ä»ĸä»¬çļĦ

-0.26

 agent

-0.25

çĲĨ

-0.25

Cra

-0.24

agents

-0.24

ä»£çĲĨäºº

-0.24

POSITIVE LOGITS

_spinner

0.27

ä¸įåĪĨ

0.26

/max

0.26

åĵº

0.25

rup

0.24

 Geneva

0.24

ICIAL

0.24

/about

0.23

 Whether

0.23

 Between

0.23

Activations Density 0.484%

Measurements

No Comments

No Known Activations