INDEX

Explanations

the

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 Hung

-0.28

ä¸¥

-0.26

chts

-0.25

ogr

-0.25

ega

-0.24

amodel

-0.24

venience

-0.24

Hung

-0.23

cul

-0.23

_errno

-0.23

POSITIVE LOGITS

 canv

0.28

ç»Ł

0.28

é¹Ń

0.26

éļ¶å±ŀ

0.25

tow

0.25

æµĩæ°´

0.25

IBM

0.25

[value

0.24

iding

0.24

IBM

0.24

Activations Density 0.006%

the

No Comments

No Known Activations