INDEX

Explanations

sensory

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_14.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.14.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Ð¿Ð°Ñģ

-0.27

_PWR

-0.27

è¿ĻæĹ¶åĢĻ

-0.27

æŃ¤æĻĤ

-0.27

kke

-0.27

 power

-0.26

IMS

-0.26

ILD

-0.25

inos

-0.25

ild

-0.25

POSITIVE LOGITS

è®©åŃ©åŃĲ

0.26

TEMPL

0.26

 kÃ½

0.24

å¿«é¤Ĳ

0.23

RITE

0.23

å¯¹çŃĸ

0.23

èħĪ

0.23

çļĦä¸Ģåĳĺ

0.23

éĤĽ

0.23

 annum

0.23

Activations Density 1.251%

sensory

No Comments

No Known Activations