INDEX

Explanations

code

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Negative Logits

åĬ¨æĢģ

-0.28

é³Ŀ

-0.26

REQ

-0.26

 tÄ©nh

-0.26

WAR

-0.25

fine

-0.25

grant

-0.25

Teen

-0.24

æĹłæĦı

-0.24

 tertiary

-0.24

POSITIVE LOGITS

 hydro

0.40

 fresh

0.31

rir

0.31

 medic

0.31

 fres

0.30

 lives

0.29

 salute

0.29

èĥ½æºĲ

0.29

hydro

0.28

çĶ¨æ°´

0.28

Activations Density 0.000%

code

No Known Activations