INDEX

Explanations

Foreign language/code

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

os

-0.36

ob

-0.34

ed

-0.34

äºĨ

-0.30

od

-0.27

 series

-0.26

In

-0.26

og

-0.26

POSITIVE LOGITS

igator

0.31

ernals

0.28

eea

0.26

 Fountain

0.25

trys

0.25

ç¥ĵ

0.25

userManager

0.25

èĬĿ

0.25

 Gros

0.25

iginal

0.24

Activations Density 0.005%

Foreign language/code

No Comments

No Known Activations