INDEX

Explanations

Roles and responsibilities

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_23.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.23.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

 convenience

-0.28

æ¢°

-0.25

äºĶçĻ¾

-0.24

 tried

-0.24

atern

-0.24

è¯¹

-0.24

é¢ĦæĸĻ

-0.24

 reuseIdentifier

-0.23

 technological

-0.23

 migrations

-0.23

POSITIVE LOGITS

ä¹Łæĺ¯å¦ĤæŃ¤

0.26

aac

0.25

orate

0.25

trÃ¤

0.25

NI

0.25

pery

0.25

pac

0.25

WI

0.25

ilk

0.24

VIC

0.24

Activations Density 0.003%

Roles and responsibilities

No Comments

No Known Activations