INDEX

Explanations

affirm

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

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

åĨĻçļĦ

-0.29

åĨĻåŃĹ

-0.28

ç¿

-0.28

ennifer

-0.27

 saja

-0.26

åıĳçĶŁçļĦ

-0.26

 separate

-0.26

 necessarily

-0.25

çļĦæłĩåĩĨ

-0.25

 standard

-0.25

POSITIVE LOGITS

advisor

0.29

asics

0.28

æĹ¥äº§

0.28

 Advisor

0.28

æĸĭ

0.27

æĢ»è®¡

0.27

æ²¡æĥ³åĪ°

0.27

ophage

0.27

itudes

0.26

icast

0.25

Activations Density 0.002%

affirm

No Comments

No Known Activations