INDEX

Explanations

schedules, plans, configurations

np_max-act · gemini-2.0-flash

New Auto-Interp

Configuration

mwhanna/qwen3-4b-transcoders/layer_7.safetensors

Prompts (Dashboard)

16,384 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

163,840

Data Type

float32

Hook Name

blocks.7.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¡®

-0.27

åħħ

-0.26

illin

-0.25

ividad

-0.24

iler

-0.24

amil

-0.24

iative

-0.24

:+:

-0.24

uild

-0.24

illez

-0.24

POSITIVE LOGITS

emm

0.27

éĩĮç¨ĭ

0.27

 fountain

0.27

 SOUR

0.26

heets

0.26

dlg

0.25

Pip

0.24

à¸§à¸²

0.24

ä¸įä»£è¡¨

0.24

å±Ĭ

0.24

Activations Density 0.000%

schedules, plans, configurations

No Comments

No Known Activations