INDEX

Explanations

but

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

odes

-0.27

Mob

-0.27

æĦı

-0.26

 lado

-0.26

Mob

-0.26

OTO

-0.24

Zwe

-0.24

Filename

-0.24

åħ¥æĪ·

-0.24

åī¥å¤º

-0.24

POSITIVE LOGITS

ucs

0.31

 Accom

0.29

elry

0.27

 fireworks

0.26

uci

0.26

æ¨µ

0.25

 Dust

0.25

 batching

0.25

 accommodations

0.25

uby

0.25

Activations Density 0.004%

but

No Comments

No Known Activations