INDEX

Explanations

induction

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_9.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.9.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

.GetBytes

-0.32

åįĥä¸ĩåĪ«

-0.27

ä¼Ĭæĭī

-0.26

ody

-0.26

sod

-0.26

 mÃ¡xima

-0.25

 stable

-0.25

ãĥĪãĥ«

-0.24

 stabilize

-0.24

ä½ľåĵģ

-0.24

POSITIVE LOGITS

 Chapel

0.29

å»ºçŃĳéĿ¢ç§¯

0.26

 templ

0.26

ToObject

0.26

templ

0.25

ulus

0.25

çļĦåĬŁæķĪ

0.25

uyáº¿t

0.25

Dom

0.25

 kami

0.25

Activations Density 1.364%

induction

No Comments

No Known Activations