INDEX

Explanations

gin

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

Hamilton

-0.30

æķĻçłĶ

-0.26

 Hamilton

-0.26

 spot

-0.25

èĭ±

-0.25

ritch

-0.24

 restoration

-0.24

ifter

-0.24

.cn

-0.24

.tencent

-0.23

POSITIVE LOGITS

ä¸ĢçĤ¹

0.28

 UserType

0.28

aran

0.27

 ($('#

0.26

æĴŃæĬ¥

0.26

oras

0.25

uran

0.25

ios

0.25

'],['

0.25

å¼ĢèįĴ

0.24

Activations Density 0.005%

gin

No Comments

No Known Activations