INDEX

Explanations

numerical comparisons

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_27.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.27.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

de

-0.28

 pros

-0.28

ÑĥÐº

-0.26

udging

-0.26

big

-0.25

mins

-0.25

Õ»

-0.25

sen

-0.24

è¹Ĵ

-0.24

cap

-0.24

POSITIVE LOGITS

 Portions

0.28

 Interfaces

0.28

 Redistributions

0.28

 Shops

0.28

elry

0.26

ç«¯

0.26

 -/↵

0.25

ORS

0.25

 Tiles

0.25

 Denied

0.25

Activations Density 0.004%

numerical comparisons

No Comments

No Known Activations