INDEX

Explanations

grateful

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

çı¥

-0.30

å¢ħ

-0.28

feit

-0.27

ä¹ħ

-0.26

æ´»è·ĥ

-0.26

 Leigh

-0.25

roup

-0.25

PropertyValue

-0.24

 concrete

-0.24

éĹ®éģĵ

-0.24

POSITIVE LOGITS

coni

0.28

idi

0.28

æ¶Īè´¹

0.27

IDI

0.27

BER

0.26

licate

0.25

 consumption

0.25

æĶ¶èİ·

0.25

ç§¤

0.24

 half

0.24

Activations Density 0.130%

grateful

No Comments

No Known Activations