INDEX

Explanations

infections

np_max-act-logits · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_25.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.25.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¦ģåĬłå¼º

-0.28

æĵİ

-0.26

esson

-0.25

iang

-0.25

ius

-0.25

cpt

-0.24

dition

-0.24

 pronto

-0.23

isd

-0.23

 GUID

-0.23

POSITIVE LOGITS

çĹħæ¯ĴæĦŁæŁĵ

0.34

evin

0.28

æ°ĳæĦı

0.26

æķ°åĢ¼

0.26

-wheel

0.26

.nodeType

0.26

çĪ¬

0.25

æľįä»İ

0.25

æ·Ģç²ī

0.24

éĴı

0.24

Activations Density 0.962%

infections

No Comments

No Known Activations