INDEX

Explanations

plaster and editorial content

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.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

.actual

-0.25

acement

-0.25

ctions

-0.25

 actual

-0.25

liament

-0.24

actual

-0.24

paypal

-0.24

://${

-0.24

reas

-0.24

gend

-0.23

POSITIVE LOGITS

ollections

0.28

otes

0.27

åįĹå±±

0.27

_mgmt

0.26

åŀĭ

0.26

otos

0.26

ias

0.25

ä¸¤é¡¹

0.25

ale

0.24

èµĦ

0.24

Activations Density 34.735%

plaster and editorial content

No Comments

No Known Activations