INDEX

Explanations

Praise, publish, depict

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

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

è¶Ĭ

-0.30

 perf

-0.27

perf

-0.26

 vessel

-0.26

Į¨

-0.25

åıī

-0.25

éļĲèº«

-0.25

è¾ľè´Ł

-0.25

jav

-0.24

 confusion

-0.24

POSITIVE LOGITS

ETING

0.26

passed

0.26

 Äĳá»īnh

0.25

 Passed

0.25

MARY

0.25

""".

0.25

epam

0.25

éĢĤæĹ¶

0.24

Passed

0.24

ixa

0.24

Activations Density 0.025%

Praise, publish, depict

No Comments

No Known Activations