INDEX

Explanations

I

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

bog

-0.29

 muddy

-0.28

æĥķ

-0.27

 need

-0.27

sag

-0.26

dee

-0.26

cce

-0.26

 Wanna

-0.26

 result

-0.25

å¼Ģ

-0.25

POSITIVE LOGITS

ynth

0.27

 recipes

0.25

 Babylon

0.25

è¿³

0.24

 Huff

0.24

ipl

0.24

çĺª

0.24

 ÑĢÐµÑĨÐµÐ¿

0.24

æ·¹

0.24

Dry

0.23

Activations Density 0.008%

I

No Comments

No Known Activations