INDEX

Explanations

constrain

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_11.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.11.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è°ĥ

-0.28

notes

-0.26

 Within

-0.26

åĸĦ

-0.25

Within

-0.25

æĸ¹

-0.25

XS

-0.24

anda

-0.24

åıĤçħ§

-0.23

Di

-0.23

POSITIVE LOGITS

hest

0.32

 Coast

0.28

è®©åŃ©åŃĲ

0.27

searchModel

0.27

HEST

0.26

ANA

0.26

äº¥

0.25

åĲ¬è¯´è¿ĩ

0.25

æľĢç¾İçļĦ

0.25

 coast

0.24

Activations Density 0.005%

constrain

No Comments

No Known Activations