INDEX

Explanations

often

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

apas

-0.28

iane

-0.25

èī³

-0.25

äºĭãģĮ

-0.24

äºĭ

-0.24

alyzer

-0.24

ographic

-0.23

 autom

-0.23

captures

-0.23

å§ĭäºİ

-0.23

POSITIVE LOGITS

åĲĮä»ģ

0.30

Ð¾Ð²Ð¾ÑĢ

0.28

AMS

0.25

vr

0.25

 Flour

0.25

Fraction

0.25

 Flynn

0.25

ç¿İ

0.24

Uri

0.24

ansa

0.24

Activations Density 0.004%

often

No Comments

No Known Activations