INDEX

Explanations

particular

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

ãĤ³ãĥ¼ãĥ

-0.28

iali

-0.26

ithmetic

-0.26

æīĭæ³ķ

-0.25

 Petroleum

-0.24

å°Ĭ

-0.24

GST

-0.24

ussels

-0.24

ç®¡çĲĨåĬŀæ³ķ

-0.24

alley

-0.24

POSITIVE LOGITS

bold

0.26

ç¤¾

0.26

ailable

0.25

éģĲ

0.25

 socially

0.25

hyp

0.25

agram

0.24

 **)&

0.24

 param

0.24

 Club

0.24

Activations Density 0.027%

particular

No Comments

No Known Activations