INDEX

Explanations

code/math formulas

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

eph

-0.32

numeric

-0.24

erm

-0.24

çªĹ

-0.24

epy

-0.24

defgroup

-0.23

éĢ¾æľŁ

-0.23

åĳ½

-0.23

sat

-0.23

Tweet

-0.23

POSITIVE LOGITS

 reverse

0.59

Reverse

0.54

 Reverse

0.54

reverse

0.53

 reversing

0.51

éĢĨ

0.50

_reverse

0.48

 backwards

0.47

 backward

0.47

 revers

0.45

Activations Density 0.003%

code/math formulas

No Comments

No Known Activations