INDEX

Explanations

progression

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

éĵ¸

-0.25

æµ·æ¹¾

-0.24

rms

-0.24

ÐµÐ±

-0.24

ãĥģ

-0.24

emia

-0.23

æ¹¾åĮº

-0.23

rior

-0.23

.Db

-0.23

 Britann

-0.23

POSITIVE LOGITS

ilet

0.30

Transport

0.29

arro

0.29

 transport

0.29

åī¯ä¹¦è®°

0.28

_transport

0.27

 transports

0.27

åĵī

0.27

 transported

0.27

imony

0.27

Activations Density 0.016%

progression

No Comments

No Known Activations