INDEX

Explanations

prime

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

INGTON

-0.29

ä½Ĳ

-0.28

æŀ¶

-0.27

å¼Ģçİ©ç¬ĳ

-0.26

 chancellor

-0.25

 carpets

-0.25

ington

-0.25

(cp

-0.24

 Trail

-0.24

ificant

-0.24

POSITIVE LOGITS

 Conce

0.32

åľĨ

0.28

å®ŀ

0.28

oks

0.27

ream

0.27

æ²ģ

0.27

een

0.27

essor

0.26

Vendor

0.26

 tamp

0.25

Activations Density 0.482%

prime

No Comments

No Known Activations