INDEX

Explanations

Aerospace and aviation

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_32.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.32.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Zar

-0.27

yps

-0.26

car

-0.26

oti

-0.26

-ps

-0.24

ritis

-0.24

ser

-0.24

ser

-0.24

iser

-0.23

ropy

-0.23

POSITIVE LOGITS

aster

0.25

styleType

0.25

asted

0.25

å¾Ĺå¤ª

0.25

ToJson

0.25

 propertyName

0.25

 Satellite

0.25

 Lambert

0.25

lifting

0.24

commercial

0.24

Activations Density 0.001%

Aerospace and aviation

No Comments

No Known Activations