INDEX

Explanations

active

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_19.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.19.mlp.hook_in

Architecture

transcoder

Context Size

8,192

Dataset

monology/pile-uncopyrighted

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

Pri

-0.30

PRI

-0.30

osal

-0.27

åİĺ

-0.26

erk

-0.26

orpor

-0.25

Taking

-0.25

çĥĤ

-0.25

 Ð¿ÑĢÐ¸Ð¼

-0.24

 Rath

-0.24

POSITIVE LOGITS

æľ¬èº«å°±æĺ¯

0.27

.Fail

0.27

pet

0.27

vou

0.26

_activity

0.25

æĿ²

0.25

æľ¬èº«çļĦ

0.24

ãģĭãģĳãĤĭ

0.24

æľ¬èº«

0.24

pet

0.24

Activations Density 0.749%

active

No Comments

No Known Activations