INDEX

Explanations

before

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

rium

-0.31

å¤ļä½Ļ

-0.30

abi

-0.26

çĬĦ

-0.26

å¤ļä½ĻçļĦ

-0.25

_regression

-0.25

 blat

-0.24

erable

-0.24

stÃ¼t

-0.23

 Ð±Ð¸Ð»

-0.23

POSITIVE LOGITS

 before

0.32

 prior

0.30

 Prior

0.29

prior

0.29

 BEFORE

0.28

Prior

0.28

Before

0.27

åħ³ç³»

0.26

before

0.26

-before

0.26

Activations Density 1.354%

before

No Comments

No Known Activations