INDEX

Explanations

head and neck

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

pen

-0.29

 pena

-0.28

Pen

-0.27

pen

-0.27

çĶ¸

-0.27

è½¬

-0.26

(nr

-0.26

olume

-0.25

çĲµ

-0.25

Pen

-0.25

POSITIVE LOGITS

 damned

0.30

èĨĪ

0.29

 fuss

0.27

åľĪåŃĲ

0.25

 getX

0.25

 Himself

0.25

 provisional

0.25

zsche

0.24

ients

0.24

 Deals

0.24

Activations Density 0.003%

head and neck

No Comments

No Known Activations