INDEX

Explanations

extend

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_1.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.1.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

å®ŀè·µä¸Ń

-0.27

Enc

-0.27

çļĦæĥħ

-0.26

æĺ¼å¤ľ

-0.26

æµĨ

-0.24

anders

-0.24

antz

-0.24

[src

-0.24

è·³

-0.23

Enc

-0.23

POSITIVE LOGITS

(extension

0.28

iete

0.26

bildung

0.26

CompleteListener

0.25

iswa

0.25

 extension

0.24

æī©å±ķ

0.24

ewear

0.24

¢åįķ

0.24

iciente

0.24

Activations Density 19.692%

extend

No Comments

No Known Activations