INDEX

Explanations

No clear pattern in tokens or texts.out

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

reno

-0.28

 reserva

-0.26

 instructional

-0.26

åĮĻ

-0.26

 instruct

-0.25

DataSource

-0.25

ç¦ģå¿Į

-0.25

æĮŀ

-0.24

ÐµÑĢÐ°

-0.24

ãĥŀãĥ³

-0.24

POSITIVE LOGITS

 hang

0.28

æ¯ıå¹´éĥ½

0.28

 sinus

0.28

Ank

0.26

nier

0.26

isted

0.25

 &↵

0.25

 ApiException

0.25

elper

0.25

 Lois

0.25

Activations Density 0.003%

No clear pattern in tokens or texts.out

No Comments

No Known Activations