INDEX

Explanations

QA forum posts

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 embedded

-0.29

æĤłæĤł

-0.27

 infused

-0.27

embedded

-0.27

 Embedded

-0.26

-aut

-0.26

 bidding

-0.26

å·¥ä½ľå²Ĺä½į

-0.25

å·¥ä½ľä¸Ń

-0.25

POSITIVE LOGITS

æłı

0.29

 newIndex

0.28

gs

0.26

áº¡n

0.26

 Chargers

0.25

libraries

0.24

å½ķ

0.24

çļĦèĢģ

0.24

 Scandin

0.24

xffffff

0.24

Activations Density 0.001%

QA forum posts

No Comments

No Known Activations