INDEX

Explanations

year old ages

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

ç¨³å®ļ

-0.31

è¶£åĳ³

-0.30

 comfort

-0.28

ç¨³å®ļçļĦ

-0.27

comfort

-0.27

orth

-0.27

æ»¡

-0.25

 satisfaction

-0.25

odate

-0.25

 compte

-0.24

POSITIVE LOGITS

éĿĴå°ĳå¹´

0.29

ä»Ķ

0.27

 girls

0.25

 noisy

0.25

å¹¼

0.25

lrt

0.24

 underage

0.24

 meas

0.24

emed

0.24

.untracked

0.24

Activations Density 0.015%

year old ages

No Comments

No Known Activations