INDEX

Explanations

ith

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

arrants

-0.26

usive

-0.25

ypical

-0.24

æĺİçŁ¥

-0.24

cul

-0.24

 classified

-0.24

 Corinth

-0.24

 gran

-0.23

.pow

-0.23

pecting

-0.23

POSITIVE LOGITS

COPE

0.29

æĢ»

0.27

ear

0.26

 ears

0.26

 Platforms

0.26

æ¼Ĥ

0.26

Ear

0.26

èĥ¥

0.25

Platforms

0.25

ç¼ł

0.24

Activations Density 1.206%

ith

No Comments

No Known Activations